BlogLLM Benchmark Scores as Published, Side by Side
Humanity’s Last Exam: Results as Published
Every result the catalog holds for Humanity’s Last Exam: 113 models from 12 developers, read from 63 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area General Knowledge and ReasoningMaintainer Center for AI Safety (CAIS) and Scale AIIntroduced 2025Data version 2026103001, as of 2026-10-30
Humanity's Last Exam is a test of about 2,500 expert-level questions across dozens of subjects, including mathematics, the humanities and the natural sciences. The items are multiple-choice or short-answer, so answers can be graded automatically. It was built because leading models had passed more than 90 percent of older tests, and at launch the most capable models scored below 10 percent.
Humanity's Last Exam (no tools)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 53.6% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: none; Fallback: with fallback |
| GPT-5.6 LunaOpenAI, released 2026-07-09 | 39.5% | IFM, IFM K2-Horizon-375B-A23B model cardchecked 2026-10-15 | Effort: max; Tools: none |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 47.2% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 5 more pages | Effort: max |
| GPT-5.6 TerraOpenAI, released 2026-07-09 | 38.5% | IFM, IFM K2-Horizon-375B-A23B model cardchecked 2026-10-15 | Effort: high; Tools: none |
| GPT-5.5OpenAI, released 2026-04-23 | 41.4% | OpenAI, Introducing GPT-5.5checked 2026-10-15; printed on 5 more pages | Effort: xhigh; Tools: none |
| GPT-5.5 ProOpenAI, released 2026-04-23 | 43.1% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | Effort: xhigh; Tools: none |
| GPT-5.4 miniOpenAI, released 2026-03-17 | 28.2% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh; Tools: none |
| GPT-5.4 nanoOpenAI, released 2026-03-17 | 24.3% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh; Tools: none |
| GPT-5.4OpenAI, released 2026-03-05 | 39.8% | OpenAI, Introducing GPT-5.4checked 2026-10-15; printed on 5 more pages | Effort: xhigh; Tools: none |
| GPT-5.4 ProOpenAI, released 2026-03-05 | 42.7% | OpenAI, Introducing GPT-5.4checked 2026-10-15; printed on 2 more pages | Effort: xhigh; Tools: none |
| GPT-5.2OpenAI, released 2025-12-11 | 34.5% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 6 more pages | Effort: xhigh; Tools: none |
| GPT-5.2 ProOpenAI, released 2025-12-11 | 36.6% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 3 more pages | Effort: xhigh; Tools: none |
| GPT-5.1OpenAI, released 2025-11-12 | 25.7% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 1 more page | Effort: high; Tools: none |
| GPT-5OpenAI, released 2025-08-07 | 6.3% | OpenAI, Introducing GPT-5checked 2026-10-15; printed on 3 more pages | Effort: none; Tools: no tools |
| 24.8% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high; Tools: no tools | |
| GPT-5 miniOpenAI, released 2025-08-07 | 18.3% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15; printed on 1 more page | Effort: high; Tools: none |
| GPT-5 ProOpenAI, released 2025-08-07 | 30.7% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high; Tools: no tools |
| gpt-oss-120bOpenAI, released 2025-08-05 | 14.9% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | Tools: none |
| gpt-oss-20bOpenAI, released 2025-08-05 | 13.76% | NVIDIA, NVIDIA Nemotron 3.5 Lightning 30B-A3B model cardchecked 2026-10-19; printed on 1 more page | Tools: none |
| ChatGPT agentOpenAI, released 2025-07-17 | 23% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high; Tools: no tools |
| o3OpenAI, released 2025-04-16 | 14.7% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high; Tools: no tools |
| GPT-4.1OpenAI, released 2025-04-14 | 3.7% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
| GPT-4oOpenAI, released 2024-05-13 | 5.3% | OpenAI, Introducing GPT-5checked 2026-10-15 | Tools: no tools |
| Claude Haiku 5.5Anthropic, released 2026-10-07 | 45.9% | Anthropic, Claude Haiku 5.5checked 2026-10-15; printed on 1 more page | Tools: none |
| Claude Sonnet 5.5Anthropic, released 2026-09-28 | 56.9% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19; printed on 2 more pages | Effort: auto; Tools: none; Attempt budget: 980k tokens per attempt |
| 56.9% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Effort: max | |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 64.4% | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25; printed on 2 more pages | Effort: max |
| Claude Fable 5.1Anthropic, released 2026-09-01 | 60.9% | Anthropic, Claude Fable 5.1 and Mythos 5.1checked 2026-10-15; printed on 3 more pages | Tools: none |
| Claude Opus 5Anthropic, released 2026-07-24 | 56.3% | Anthropic, Claude Opus 5checked 2026-10-15; printed on 6 more pages | Tools: none |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 43.2% | Anthropic, Claude Sonnet 5checked 2026-10-15; printed on 2 more pages | Tools: none |
| Claude Fable 5Anthropic, released 2026-06-09 | 57.8% | Anthropic, Claude Fable 5.1 and Mythos 5.1checked 2026-10-15; printed on 6 more pages | Tools: none |
| Claude Mythos 5Anthropic, released 2026-06-09 | 59% | Anthropic, Claude Fable 5 and Claude Mythos 5checked 2026-10-15 | Tools: none |
| Claude Opus 4.8Anthropic, released 2026-05-28 | 49.8% | Anthropic, Claude Opus 4.8checked 2026-10-15; printed on 7 more pages | Tools: none |
| Claude Opus 4.7Anthropic, released 2026-04-16 | 46.9% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 3 more pages | Tools: none |
| Claude Mythos PreviewAnthropic, released 2026-04-07 | 56.8% | Anthropic, Claude Fable 5 and Claude Mythos 5checked 2026-10-15; printed on 1 more page | Tools: none |
| Claude Sonnet 4.6Anthropic, released 2026-02-17 | 33.2% | Anthropic, Claude Sonnet 4.6checked 2026-10-15; printed on 3 more pages | Effort: max; Tools: none |
| Claude Opus 4.6Anthropic, released 2026-02-05 | 40% | Anthropic, Claude Opus 4.6checked 2026-10-15; printed on 9 more pages | Effort: max; Tools: none |
| Claude Opus 4.5Anthropic, released 2025-11-24 | 30.8% | Anthropic, Claude Opus 4.6checked 2026-10-15; printed on 6 more pages | Effort: max; Tools: none |
| Claude Haiku 4.5Anthropic, released 2025-10-15 | 10.2% | Anthropic, Claude Haiku 5.5checked 2026-10-15; printed on 1 more page | Tools: none |
| Claude Sonnet 4.5Anthropic, released 2025-09-29 | 17.7% | Anthropic, Claude Opus 4.6checked 2026-10-15; printed on 5 more pages | Effort: max; Tools: none |
| Claude Opus 4Anthropic, released 2025-05-22 | 7.1% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | Effort: no extended thinking |
| Claude Sonnet 4Anthropic, released 2025-05-22 | 5.8% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | Effort: no extended thinking |
| Gemini 3.5 FlashGoogle, released 2026-05-19 | 40.2% | Google, Gemini 3.5 Flash model cardchecked 2026-10-15 | - |
| Gemma 4 12BGoogle, released 2026-04-02 | 5.2% | Google, Gemma 4 model cardchecked 2026-10-15 | Tools: none |
| Gemma 4 26B A4BGoogle, released 2026-04-02 | 8.7% | Google, Gemma 4 model cardchecked 2026-10-15; printed on 3 more pages | Tools: none |
| Gemma 4 31BGoogle, released 2026-04-02 | 19.5% | Google, Gemma 4 model cardchecked 2026-10-15; printed on 2 more pages | Tools: none |
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 44.4% | Google, Gemini 3.1 Pro model cardchecked 2026-10-15; printed on 10 more pages | Effort: high; Tools: none |
| Gemini 3 FlashGoogle, released 2025-12-17 | 33.7% | Google, Gemini 3.5 Flash model cardchecked 2026-10-15 | - |
| Gemini 3 ProGoogle, released 2025-11-18 | 37.5% | Google, Gemini 3.1 Pro model cardchecked 2026-10-15; printed on 8 more pages | Effort: high; Tools: none |
| Gemini 2.5 FlashGoogle, released 2025-05-20 | 5.6% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
| Grok 4xAI, released 2025-07-09 | 25.4% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: none |
| Muse Glimmer-30BMeta, released 2026-08-09 | 22% | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15 | - |
| DeepSeek-V4.1-Flash-1017DeepSeek, released 2026-10-17 | 42.6% | DeepSeek, DeepSeek-V4.1-Flash-1017 model cardchecked 2026-10-18; printed on 2 more pages | - |
| 44% | DeepSeek, DeepSeek-V4.1-Flash-1017 model cardchecked 2026-10-18 | Dataset revision: text-only subset of HLE (dagger on the card) | |
| DeepSeek-V4.1-FlashDeepSeek, released 2026-09-10 | 39.1% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 2 more pages | Effort: max; Dataset revision: text-only subset of HLE (dagger on the card) |
| 36.8% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max | |
| DeepSeek-V4-Flash (Preview)DeepSeek, released 2026-04-24 | 34.8% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15; printed on 2 more pages | Effort: max; Tools: none |
| 29.4% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: high; Tools: none | |
| 8.1% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: non-think; Tools: none | |
| DeepSeek-V4-Pro (Preview)DeepSeek, released 2026-04-24 | 7.7% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15; printed on 4 more pages | Effort: non-think; Tools: none |
| 34.5% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: high; Tools: none | |
| 37.7% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: max; Tools: none | |
| DeepSeek-V3.2DeepSeek, released 2025-12-01 | 25.1% | DeepSeek, DeepSeek-V3.2 model cardchecked 2026-10-15; printed on 4 more pages | Effort: thinking |
| DeepSeek-V3.2-SpecialeDeepSeek, released 2025-12-01 | 30.6% | DeepSeek, DeepSeek-V3.2 model cardchecked 2026-10-15 | - |
| DeepSeek-V3.2-ExpDeepSeek, released 2025-09-29 | 19.8% | DeepSeek, DeepSeek-V3.2-Exp model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| DeepSeek-V3.1-TerminusDeepSeek, released 2025-09-22 | 21.7% | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| DeepSeek-V3.1DeepSeek, released 2025-08-21 | 15.9% | DeepSeek, DeepSeek-V3.1-Terminus model cardchecked 2026-10-15 | Tools: none |
| DeepSeek-R1-0528DeepSeek, released 2025-05-28 | 17.7% | DeepSeek, DeepSeek-R1-0528 model cardchecked 2026-10-15 | Tools: none |
| DeepSeek-V3-0324DeepSeek, released 2025-03-24 | 5.2% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
| DeepSeek-R1DeepSeek, released 2025-01-20 | 8.5% | DeepSeek, DeepSeek-R1-0528 model cardchecked 2026-10-15 | Tools: none |
| DeepSeek-V4-Flash-0731DeepSeek | 37.8% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 3 more pages | Effort: max; Dataset revision: text-only subset of HLE (dagger on the card) |
| DeepSeek-V4-Pro-0813DeepSeek | 42.7% | DeepSeek, DeepSeek-V4-Pro-0813 model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| Qwen3.8-MaxAlibaba, released 2026-08-03 | 43.6% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Qwen3.7-PlusAlibaba, released 2026-06-01 | 34.7% | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.6-27BAlibaba, released 2026-04-22 | 24% | Alibaba, Qwen3.6-27B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.6-35B-A3BAlibaba, released 2026-04-16 | 21.4% | Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15; printed on 3 more pages | - |
| Qwen3.6-PlusAlibaba, released 2026-04-02 | 28.8% | Z.ai, GLM-5.1 model cardchecked 2026-10-15 | Tools: none |
| Qwen3.5-122B-A10BAlibaba, released 2026-02-24 | 25.3% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| Qwen3.5-27BAlibaba, released 2026-02-24 | 24.3% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 2 more pages | Tools: none |
| Qwen3.5-35B-A3BAlibaba, released 2026-02-24 | 22.4% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| Qwen3.5-397B-A17BAlibaba, released 2026-02-16 | 28.7% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15; printed on 2 more pages | - |
| Qwen3-30B-A3B-Thinking-2507Alibaba, released 2025-07-30 | 9.8% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking; Tools: none |
| Qwen3-235B-A22BAlibaba, released 2025-04-29 | 18.2% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| Qwen3-Max-ThinkingAlibaba | 30.2% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Qwen3.7-MaxAlibaba | 41.4% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 1 more page | - |
| Qwen3.8-27BAlibaba | 30.8% | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.8-Flash-NextAlibaba | 35.9% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15; printed on 1 more page | - |
| Kimi K3.1 ProMoonshot AI, released 2026-10-23 | 51.1% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: none |
| Kimi K3Moonshot AI, released 2026-07-16 | 43.5% | Moonshot AI, Kimi K3 model cardchecked 2026-10-15; printed on 4 more pages | Effort: max; Tools: none |
| Kimi K2.6Moonshot AI, released 2026-04-20 | 34.7% | Moonshot AI, Kimi K2.6 model cardchecked 2026-10-15; printed on 3 more pages | Tools: none |
| Kimi K2.5Moonshot AI, released 2026-01-27 | 30.1% | Moonshot AI, Kimi K2.5 model cardchecked 2026-10-15; printed on 5 more pages | Tools: none |
| Kimi K2 ThinkingMoonshot AI, released 2025-11-06 | 23.9% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15; printed on 1 more page | Effort: thinking; Tools: none |
| Kimi K2 Instruct 0905Moonshot AI, released 2025-09-05 | 7.9% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: none |
| Kimi K2 InstructMoonshot AI, released 2025-07-11 | 4.7% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
| GLM-5.3-FlashZ.ai, released 2026-08-26 | 36.47% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| GLM-5.3Z.ai, released 2026-08-18 | 42% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 3 more pages | Dataset revision: text-only subset of HLE (dagger on the card) |
| GLM-5.2Z.ai, released 2026-06-16 | 40.5% | Z.ai, GLM-5.2 model cardchecked 2026-10-15; printed on 3 more pages | Tools: none |
| GLM-5.1Z.ai, released 2026-04-07 | 31% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 3 more pages | Tools: none |
| GLM-5Z.ai, released 2026-02-12 | 30.5% | Z.ai, GLM-5 model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| GLM-4.7Z.ai, released 2025-12-22 | 24.8% | Z.ai, GLM-4.7 model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| GLM-4.6Z.ai, released 2025-09-30 | 17.2% | Z.ai, GLM-4.7 model cardchecked 2026-10-15 | Tools: none |
| MiniMax-M3.1-FlashMiniMax, released 2026-10-19 | 43.4% | MiniMax, MiniMax-M3.1-Flash model cardchecked 2026-10-25 | Tools: none; Dataset revision: text-only subset (2,158 questions) |
| MiniMax M3MiniMax, released 2026-06-01 | 39% | IFM, IFM K2-Horizon-375B-A23B model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| MiniMax M2.7MiniMax, released 2026-03-18 | 23.1% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| MiniMax M2.5MiniMax, released 2026-02-12 | 19.4% | MiniMax, MiniMax-M2.5 model cardchecked 2026-10-15 | Tools: none |
| MiniMax M2.1MiniMax, released 2025-12-20 | 22.2% | MiniMax, MiniMax-M2.5 model cardchecked 2026-10-15 | Tools: none |
| Nemotron 3.5 Bolt 74B-A9BNVIDIA, released 2026-10-15 | 25.3% | NVIDIA, NVIDIA Nemotron 3.5 Bolt 74B-A9B model cardchecked 2026-10-19 | Tools: none; Model as printed: Nemotron 3.5 Bolt 74B-A9B-24GB (IQ2) |
| 28.73% | NVIDIA, NVIDIA Nemotron 3.5 Bolt 74B-A9B model cardchecked 2026-10-19 | Tools: none; Model as printed: Nemotron 3.5 Bolt 74B-A9B (BF16) | |
| Nemotron 3.5 Super VL 120B-A12BNVIDIA, released 2026-10-15 | 31.79% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| Nemotron 3.5 Lightning 30B-A3BNVIDIA, released 2026-08-11 | 10.47% | NVIDIA, NVIDIA Nemotron 3.5 Bolt 74B-A9B model cardchecked 2026-10-19; printed on 1 more page | Tools: none |
| Nemotron 3 UltraNVIDIA, released 2026-06-04 | 29.2% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19; printed on 3 more pages | - |
| Nemotron 3 SuperNVIDIA, released 2026-03-11 | 20.3% | NVIDIA, NVIDIA Nemotron 3.5 Lightning 30B-A3B model cardchecked 2026-10-19 | Tools: none |
| Nemotron 3 Nano 30B-A3BNVIDIA, released 2025-12-15 | 10.89% | NVIDIA, NVIDIA Nemotron 3.5 Lightning 30B-A3B model cardchecked 2026-10-19; printed on 1 more page | Tools: none |
| InklingThinking Machines, released 2026-07-14 | 29.7% | Thinking Machines, Thinking Machines Inkling model cardchecked 2026-10-15; printed on 1 more page | Effort: 0.99; Tools: none |
| Inkling-SmallThinking Machines | 33.3% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Humanity's Last Exam (with tools)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 57.2% | OpenAI, GPT-6 Astrachecked 2026-10-14; printed on 3 more pages | Tools: enabled; exact tools in source |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 58% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 3 more pages | Effort: max; Tools: enabled; exact tools in source |
| GPT-5.5OpenAI, released 2026-04-23 | 52.2% | OpenAI, Introducing GPT-5.5checked 2026-10-15; printed on 4 more pages | Effort: xhigh; Tools: with tools |
| GPT-5.5 ProOpenAI, released 2026-04-23 | 57.2% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | Effort: xhigh; Tools: with tools |
| GPT-5.4 miniOpenAI, released 2026-03-17 | 41.5% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh; Tools: with tools |
| GPT-5.4 nanoOpenAI, released 2026-03-17 | 37.7% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: xhigh; Tools: with tools |
| GPT-5.4OpenAI, released 2026-03-05 | 52.1% | OpenAI, Introducing GPT-5.4checked 2026-10-15; printed on 5 more pages | Effort: xhigh; Tools: with tools |
| GPT-5.4 ProOpenAI, released 2026-03-05 | 58.7% | OpenAI, Introducing GPT-5.4checked 2026-10-15; printed on 2 more pages | Effort: xhigh; Tools: with tools |
| GPT-5.2OpenAI, released 2025-12-11 | 45.5% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 5 more pages | Effort: xhigh; Tools: search, python |
| GPT-5.2 ProOpenAI, released 2025-12-11 | 50% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 3 more pages | Effort: xhigh; Tools: search, python |
| GPT-5.1OpenAI, released 2025-11-12 | 42.7% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 1 more page | Effort: high; Tools: search, python |
| GPT-5OpenAI, released 2025-08-07 | 35.2% | OpenAI, Introducing GPT-5checked 2026-10-15; printed on 2 more pages | Effort: high; Tools: python + search with blocklist |
| GPT-5 miniOpenAI, released 2025-08-07 | 31.6% | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15; printed on 1 more page | Effort: high; Tools: with tools |
| GPT-5 ProOpenAI, released 2025-08-07 | 42% | OpenAI, Introducing GPT-5checked 2026-10-15; printed on 1 more page | Effort: high; Tools: python + search with blocklist |
| gpt-oss-120bOpenAI, released 2025-08-05 | 19% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | Tools: enabled; search; Context: 256000 |
| gpt-oss-20bOpenAI, released 2025-08-05 | 17.3% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Tools: with tools |
| ChatGPT agentOpenAI, released 2025-07-17 | 41.6% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high; Tools: browser + computer + terminal |
| o3OpenAI, released 2025-04-16 | 24.3% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high; Tools: python + browser |
| Deep researchOpenAI, released 2025-02-02 | 26.6% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high; Tools: python + browser |
| Claude Haiku 5.5Anthropic, released 2026-10-07 | 57.4% | Anthropic, Claude Haiku 5.5checked 2026-10-15; printed on 1 more page | Tools: enabled; exact tools in source |
| Claude Sonnet 5.5Anthropic, released 2026-09-28 | 64.5% | Anthropic, Claude Sonnet 5.5checked 2026-10-14; printed on 3 more pages | Tools: enabled; exact tools in source |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 67.7% | Anthropic, Claude Opus 5.5checked 2026-10-14; printed on 4 more pages | Tools: enabled; exact tools in source |
| Claude Fable 5.1Anthropic, released 2026-09-01 | 65% | Anthropic, Claude Fable 5.1 and Mythos 5.1checked 2026-10-15; printed on 5 more pages | Tools: enabled; exact tools in source |
| Claude Opus 5Anthropic, released 2026-07-24 | 64.7% | Anthropic, Claude Opus 5checked 2026-10-15; printed on 6 more pages | Tools: enabled; exact tools in source |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 57.4% | Anthropic, Claude Sonnet 5checked 2026-10-15; printed on 2 more pages | Tools: enabled; exact tools in source |
| Claude Fable 5Anthropic, released 2026-06-09 | 63.8% | Anthropic, Claude Fable 5.1 and Mythos 5.1checked 2026-10-15; printed on 8 more pages | Tools: enabled; exact tools in source |
| Claude Mythos 5Anthropic, released 2026-06-09 | 64.5% | Anthropic, Claude Fable 5 and Claude Mythos 5checked 2026-10-15 | Tools: enabled; exact tools in source |
| Claude Opus 4.8Anthropic, released 2026-05-28 | 57.9% | Anthropic, Claude Opus 4.8checked 2026-10-15; printed on 9 more pages | Tools: enabled; exact tools in source |
| Claude Opus 4.7Anthropic, released 2026-04-16 | 54.7% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 2 more pages | Tools: enabled; exact tools in source |
| Claude Mythos PreviewAnthropic, released 2026-04-07 | 64.7% | Anthropic, Claude Fable 5 and Claude Mythos 5checked 2026-10-15; printed on 1 more page | Tools: enabled; exact tools in source |
| Claude Sonnet 4.6Anthropic, released 2026-02-17 | 49% | Anthropic, Claude Sonnet 4.6checked 2026-10-15; printed on 2 more pages | Effort: max; Tools: enabled; exact tools in source |
| Claude Opus 4.6Anthropic, released 2026-02-05 | 53% | Anthropic, Claude Opus 4.6checked 2026-10-15; printed on 6 more pages | Effort: max; Tools: enabled; exact tools in source |
| Claude Opus 4.5Anthropic, released 2025-11-24 | 43.4% | Anthropic, Claude Opus 4.6checked 2026-10-15; printed on 4 more pages | Effort: max; Tools: enabled; exact tools in source |
| Claude Haiku 4.5Anthropic, released 2025-10-15 | 18.7% | Anthropic, Claude Haiku 5.5checked 2026-10-15; printed on 1 more page | Tools: enabled; exact tools in source |
| Claude Sonnet 4.5Anthropic, released 2025-09-29 | 33.6% | Anthropic, Claude Opus 4.6checked 2026-10-15; printed on 3 more pages | Effort: max; Tools: enabled; exact tools in source |
| Gemma 4 26B A4BGoogle, released 2026-04-02 | 17.2% | Google, Gemma 4 model cardchecked 2026-10-15 | Tools: search |
| Gemma 4 31BGoogle, released 2026-04-02 | 26.5% | Google, Gemma 4 model cardchecked 2026-10-15 | Tools: search |
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 51.4% | Google, Gemini 3.1 Pro model cardchecked 2026-10-15; printed on 9 more pages | Effort: high; Tools: search (blocklist), code |
| Gemini 3 ProGoogle, released 2025-11-18 | 45.8% | Google, Gemini 3.1 Pro model cardchecked 2026-10-15; printed on 6 more pages | Effort: high; Tools: search (blocklist), code |
| Grok 4xAI, released 2025-07-09 | 41% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: enabled; search, code interpreter, web browsing; Context: 256000 |
| 50.7% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Harness: heavy mode: 8 parallel trajectories, aggregated; Tools: enabled; search, code interpreter, web browsing; Context: 256000 | |
| Muse Spark OpenMeta, released 2026-10-15 | 61% | Meta, Meta Muse Spark Open 816B-A42B model cardchecked 2026-10-19 | Effort: xhigh; Tools: with tools |
| DeepSeek-V4.1-Flash-1017DeepSeek, released 2026-10-17 | 58.8% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: with tools |
| DeepSeek-V4.1-FlashDeepSeek, released 2026-09-10 | 63.9% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Tools: enabled; exact tools in source |
| DeepSeek-V4-Flash (Preview)DeepSeek, released 2026-04-24 | 45.1% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15; printed on 2 more pages | Effort: max; Tools: enabled; exact tools in source |
| 40.3% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: high; Tools: enabled; exact tools in source | |
| DeepSeek-V4-Pro (Preview)DeepSeek, released 2026-04-24 | 44.7% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15; printed on 4 more pages | Effort: high; Tools: enabled; exact tools in source |
| 48.2% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: max; Tools: enabled; exact tools in source | |
| DeepSeek-V3.2DeepSeek, released 2025-12-01 | 40.8% | Moonshot AI, Kimi K2.5 model cardchecked 2026-10-15; printed on 3 more pages | Tools: search, code interpreter, browsing |
| DeepSeek-V3.2-ExpDeepSeek, released 2025-09-29 | 20.3% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: enabled; search, code interpreter, web browsing; Context: 256000 |
| DeepSeek-V4-Flash-0731DeepSeek | 51.5% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 1 more page | Effort: max; Tools: enabled; exact tools in source |
| DeepSeek-V4-Pro-0813DeepSeek | 60% | DeepSeek, DeepSeek-V4-Pro-0813 model cardchecked 2026-10-15; printed on 2 more pages | Tools: enabled; exact tools in source |
| DeepSeek-V4-Vision-ExpDeepSeek | 55.1% | Z.ai, Z.ai GLM-5.3-Flash model cardchecked 2026-10-15 | Tools: tools |
| Qwen3.8-MaxAlibaba, released 2026-08-03 | 56.2% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 1 more page | Tools: enabled; exact tools in source |
| Qwen3.6-PlusAlibaba, released 2026-04-02 | 50.6% | Z.ai, GLM-5.1 model cardchecked 2026-10-15 | Tools: tools |
| Qwen3.5-122B-A10BAlibaba, released 2026-02-24 | 47.5% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | Tools: enabled; search; Context: 256000 |
| Qwen3.5-27BAlibaba, released 2026-02-24 | 48.5% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | Tools: enabled; search; Context: 256000 |
| Qwen3.5-35B-A3BAlibaba, released 2026-02-24 | 47.4% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | Tools: enabled; search; Context: 256000 |
| Qwen3.5-397B-A17BAlibaba, released 2026-02-16 | 48.3% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15; printed on 1 more page | Tools: enabled; search; Context: 256000 |
| Qwen3-Max-ThinkingAlibaba | 49.8% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | Tools: enabled; search; Context: 256000 |
| Qwen3.7-MaxAlibaba | 53.5% | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14; printed on 1 more page | Tools: enabled; exact tools in source |
| Qwen3.8-2.4T-A95BAlibaba | 56.2% | Meta, Meta Muse Spark Open 816B-A42B model cardchecked 2026-10-19 | Effort: xhigh; Tools: with tools |
| Kimi K3.1 ProMoonshot AI, released 2026-10-23 | 70% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: with tools |
| Kimi K3Moonshot AI, released 2026-07-16 | 56% | Moonshot AI, Kimi K3 model cardchecked 2026-10-15; printed on 4 more pages | Effort: max; Tools: enabled; general tools |
| Kimi K2.6Moonshot AI, released 2026-04-20 | 54% | Moonshot AI, Kimi K2.6 model cardchecked 2026-10-15; printed on 3 more pages | Tools: search, code interpreter, browsing; Context: 262144 |
| Kimi K2.5Moonshot AI, released 2026-01-27 | 50.2% | Moonshot AI, Kimi K2.5 model cardchecked 2026-10-15; printed on 5 more pages | Tools: search, code interpreter, browsing |
| Kimi K2 ThinkingMoonshot AI, released 2025-11-06 | 51% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15; printed on 1 more page | Effort: thinking; Harness: heavy mode: 8 parallel trajectories, aggregated; Tools: enabled; search, code interpreter, web browsing; Context: 256000 |
| 44.9% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Effort: thinking; Tools: enabled; search, code interpreter, web browsing; Context: 256000 | |
| Kimi K2 Instruct 0905Moonshot AI, released 2025-09-05 | 21.7% | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: enabled; search, code interpreter, web browsing; Context: 256000 |
| GLM-5.3-FlashZ.ai, released 2026-08-26 | 55.3% | Z.ai, Z.ai GLM-5.3-Flash model cardchecked 2026-10-15 | Effort: max; Tools: tools |
| GLM-5.3Z.ai, released 2026-08-18 | 62.5% | Z.ai, GLM-5.3 model cardchecked 2026-10-15; printed on 3 more pages | Effort: max; Context: 300000 |
| GLM-5.2Z.ai, released 2026-06-16 | 54.7% | Z.ai, GLM-5.2 model cardchecked 2026-10-15; printed on 4 more pages | Tools: tools; Context: 300000 |
| GLM-5.1Z.ai, released 2026-04-07 | 52.3% | Z.ai, GLM-5.1 model cardchecked 2026-10-15; printed on 3 more pages | Tools: tools |
| GLM-5Z.ai, released 2026-02-12 | 50.4% | Z.ai, GLM-5 model cardchecked 2026-10-15; printed on 1 more page | Tools: tools; Context: 202752 |
| GLM-4.7Z.ai, released 2025-12-22 | 42.8% | Z.ai, GLM-4.7 model cardchecked 2026-10-15; printed on 1 more page | Tools: tools |
| GLM-4.6Z.ai, released 2025-09-30 | 30.4% | Z.ai, GLM-4.7 model cardchecked 2026-10-15 | Tools: tools |
| Nemotron 3 UltraNVIDIA, released 2026-06-04 | 37.4% | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15; printed on 2 more pages | Tools: with tools |
| Nemotron 3 Nano 30B-A3BNVIDIA, released 2025-12-15 | 15.5% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Tools: with tools |
| InklingThinking Machines, released 2026-07-14 | 46% | Thinking Machines, Thinking Machines Inkling model cardchecked 2026-10-15; printed on 1 more page | Effort: 0.99; Tools: with tools |
Humanity's Last Exam (Verified)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.6 SolOpenAI, released 2026-07-09 | 54.5% | Google, Gemini 3.8 Flash model cardchecked 2026-10-15 | - |
| GPT-5.6 TerraOpenAI, released 2026-07-09 | 51.1% | Google, Gemini 3.7 Flash model cardchecked 2026-10-15; printed on 1 more page | - |
| GPT-5.2OpenAI, released 2025-12-11 | 43.3% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Claude Opus 5Anthropic, released 2026-07-24 | 54.4% | Google, Gemini 3.8 Flash model cardchecked 2026-10-15 | - |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 31% | Google, Gemini 3.7 Flash model cardchecked 2026-10-15; printed on 1 more page | - |
| Claude Opus 4.5Anthropic, released 2025-11-24 | 38.8% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Gemini 3.8 FlashGoogle, released 2026-09-02 | 54.9% | Google, Gemini 3.8 Flash model cardchecked 2026-10-15 | - |
| Gemini 3.7 FlashGoogle, released 2026-08-13 | 53.6% | Google, Gemini 3.7 Flash model cardchecked 2026-10-15; printed on 1 more page | - |
| Gemini 3.6 FlashGoogle, released 2026-07-21 | 51.2% | Google, Gemini 3.7 Flash model cardchecked 2026-10-15 | - |
| Gemini 3 ProGoogle, released 2025-11-18 | 48% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Qwen3.5-397B-A17BAlibaba, released 2026-02-16 | 37.6% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Qwen3-Max-ThinkingAlibaba | 37.6% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
Humanity's Last Exam Diamond (no tools)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 65.8% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: none; Fallback: with fallback |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 60.9% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: none; Fallback: with fallback |
| Claude Fable 5.1Anthropic, released 2026-09-01 | 55.1% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: none; Fallback: with fallback |
| Muse Spark OpenMeta, released 2026-10-15 | 26.1% | Meta, Meta Muse Spark Open 816B-A42B model cardchecked 2026-10-19 | Effort: xhigh; Tools: none |
| DeepSeek-V4.1-Flash-1017DeepSeek, released 2026-10-17 | 21.6% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: none |
| Qwen3.8-2.4T-A95BAlibaba | 17.3% | Meta, Meta Muse Spark Open 816B-A42B model cardchecked 2026-10-19 | Effort: xhigh; Tools: none |
| Kimi K3.1 ProMoonshot AI, released 2026-10-23 | 39.4% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Tools: none |
| Kimi K3Moonshot AI, released 2026-07-16 | 22.2% | Meta, Meta Muse Spark Open 816B-A42B model cardchecked 2026-10-19 | Effort: max; Tools: none |
| GLM-5.3Z.ai, released 2026-08-18 | 16.4% | Meta, Meta Muse Spark Open 816B-A42B model cardchecked 2026-10-19; printed on 1 more page | Effort: max; Tools: none |
| Nemotron 3 UltraNVIDIA, released 2026-06-04 | 8.9% | Meta, Meta Muse Spark Open 816B-A42B model cardchecked 2026-10-19 | Tools: none |
| InklingThinking Machines, released 2026-07-14 | 11.2% | Meta, Meta Muse Spark Open 816B-A42B model cardchecked 2026-10-19 | Effort: xhigh; Tools: none |
Humanity's Last Exam (full set, tools not stated)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Qwen3.5-122B-A10BAlibaba, released 2026-02-24 | 24.4% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| Qwen3.8-Flash-NextAlibaba | 38.8% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| GLM-5.3-FlashZ.ai, released 2026-08-26 | 35.1% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| Nemotron 3.5 Super VL 120B-A12BNVIDIA, released 2026-10-15 | 29.2% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| Inkling-SmallThinking Machines | 31.6% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.