BlogLLM Benchmark Scores as Published, Side by Side
SuperGPQA: Results as Published
Every result the catalog holds for SuperGPQA: 25 models from 6 developers, read from 6 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 Science and MathMaintainer M-A-P team and ByteDance (Xinrun Du and co-authors)Introduced 2025Data version 2026103001, as of 2026-10-30
SuperGPQA tests graduate-level knowledge and reasoning across 285 disciplines, including applied fields that other benchmarks leave out, with questions filtered by experts and models. The score is accuracy.
SuperGPQA
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.2OpenAI, released 2025-12-11 | 67.9% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| GPT-5 miniOpenAI, released 2025-08-07 | 58.6% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| gpt-oss-120bOpenAI, released 2025-08-05 | 54.6% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| GPT-4.1OpenAI, released 2025-04-14 | 50.8% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
| Claude Opus 4.5Anthropic, released 2025-11-24 | 70.6% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15; printed on 1 more page | - |
| Claude Opus 4Anthropic, released 2025-05-22 | 56.5% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | Effort: no extended thinking |
| Claude Sonnet 4Anthropic, released 2025-05-22 | 55.7% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | Effort: no extended thinking |
| Gemma 4 26B A4BGoogle, released 2026-04-02 | 61.4% | Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15 | - |
| Gemma 4 31BGoogle, released 2026-04-02 | 65.7% | Alibaba, Qwen3.6-27B model cardchecked 2026-10-15; printed on 1 more page | - |
| Gemini 3 ProGoogle, released 2025-11-18 | 74% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Gemini 2.5 FlashGoogle, released 2025-05-20 | 49.6% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
| DeepSeek-V4-Flash-BaseDeepSeek, released 2026-04-24 | 46.5% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| DeepSeek-V4-Pro-BaseDeepSeek, released 2026-04-24 | 53.9% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| DeepSeek-V3.2-BaseDeepSeek, released 2025-12-01 | 45% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| DeepSeek-V3-0324DeepSeek, released 2025-03-24 | 53.7% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
| Qwen3.6-27BAlibaba, released 2026-04-22 | 66% | Alibaba, Qwen3.6-27B model cardchecked 2026-10-15 | - |
| Qwen3.6-35B-A3BAlibaba, released 2026-04-16 | 64.7% | Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.5-122B-A10BAlibaba, released 2026-02-24 | 67.1% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| Qwen3.5-27BAlibaba, released 2026-02-24 | 65.6% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 2 more pages | - |
| Qwen3.5-35B-A3BAlibaba, released 2026-02-24 | 63.4% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.5-397B-A17BAlibaba, released 2026-02-16 | 70.4% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3-235B-A22BAlibaba, released 2025-04-29 | 64.9% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3-Max-ThinkingAlibaba | 67.3% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Kimi K2.5Moonshot AI, released 2026-01-27 | 69.2% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Kimi K2 InstructMoonshot AI, released 2025-07-11 | 57.2% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
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.