BlogLLM Benchmark Scores as Published, Side by Side
FrontierMath: Results as Published
Every result the catalog holds for FrontierMath: 26 models from 7 developers, read from 8 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 Epoch AIIntroduced 2024Data version 2026103001, as of 2026-10-30
FrontierMath is a set of research-level mathematics problems written by professional mathematicians across most branches of modern maths. Tier 4 is its hardest part, with 43 problems in version 2 (released June 12, 2026). Answers are checked automatically: the model must submit a short Python function that returns the final answer within 30 seconds, and each problem scores 1 or 0.
FrontierMath Tier 1-3
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.5OpenAI, released 2026-04-23 | 51.7% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | Effort: xhigh |
| GPT-5.5 ProOpenAI, released 2026-04-23 | 52.4% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | Effort: xhigh |
| GPT-5.4OpenAI, released 2026-03-05 | 47.6% | OpenAI, Introducing GPT-5.4checked 2026-10-15; printed on 1 more page | Effort: xhigh |
| GPT-5.4 ProOpenAI, released 2026-03-05 | 50% | OpenAI, Introducing GPT-5.4checked 2026-10-15; printed on 1 more page | Effort: xhigh |
| GPT-5.2OpenAI, released 2025-12-11 | 40.3% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 1 more page | Effort: xhigh; Tools: python |
| GPT-5.1OpenAI, released 2025-11-12 | 26.7% | OpenAI, Introducing GPT-5.1 for developerschecked 2026-10-15; printed on 1 more page | Effort: high; Tools: python |
| GPT-5OpenAI, released 2025-08-07 | 26.3% | OpenAI, Introducing GPT-5checked 2026-10-15; printed on 1 more page | Effort: high; Tools: python |
| 13.5% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high; Tools: no tools | |
| GPT-5 ProOpenAI, released 2025-08-07 | 32.1% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high; Tools: python |
| ChatGPT agentOpenAI, released 2025-07-17 | 27.4% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high; Tools: browser + computer + terminal |
| o3OpenAI, released 2025-04-16 | 15.8% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high; Tools: python |
| OpenAI o4-miniOpenAI, released 2025-04-16 | 19.3% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high; Tools: python |
| Claude Opus 4.7Anthropic, released 2026-04-16 | 43.8% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | - |
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 36.9% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | - |
FrontierMath Tier 4 (v2)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 97.6% | OpenAI, GPT-6 Astrachecked 2026-10-14 | - |
| GPT-5.6 LunaOpenAI, released 2026-07-09 | 58.5% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15 | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 83% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15; printed on 1 more page | - |
| GPT-5.6 TerraOpenAI, released 2026-07-09 | 68.3% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15 | - |
| GPT-5.5OpenAI, released 2026-04-23 | 72.5% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15 | - |
| Claude Fable 5.1Anthropic, released 2026-09-01 | 87.8% | OpenAI, GPT-6 Astrachecked 2026-10-14 | - |
| Claude Opus 5Anthropic, released 2026-07-24 | 73.2% | OpenAI, GPT-6 Astrachecked 2026-10-14 | - |
| Claude Fable 5Anthropic, released 2026-06-09 | 87.8% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15; printed on 1 more page | - |
| Claude Opus 4.8Anthropic, released 2026-05-28 | 56.1% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15 | - |
| Grok 4.7xAI, released 2026-09-21 | 17.1% | Epoch AI, Epoch AI Benchmarking Hubchecked 2026-10-30 | Effort: xhigh |
| DeepSeek-V4.1-Flash-1017DeepSeek, released 2026-10-17 | 46.3% | Epoch AI, Epoch AI Benchmarking Hubchecked 2026-10-30 | Effort: max |
| Qwen3.8-MaxAlibaba, released 2026-08-03 | 46.3% | Epoch AI, Epoch AI Benchmarking Hubchecked 2026-10-30 | Effort: xhigh |
| GLM-5.3Z.ai, released 2026-08-18 | 29.3% | Epoch AI, Epoch AI Benchmarking Hubchecked 2026-10-30 | Effort: max |
FrontierMath Tier 1-3 (v2)
FrontierMath Tier 4
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.5OpenAI, released 2026-04-23 | 35.4% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | Effort: xhigh |
| GPT-5.5 ProOpenAI, released 2026-04-23 | 39.6% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | Effort: xhigh |
| GPT-5.4OpenAI, released 2026-03-05 | 27.1% | OpenAI, Introducing GPT-5.4checked 2026-10-15; printed on 1 more page | Effort: xhigh |
| GPT-5.4 ProOpenAI, released 2026-03-05 | 38% | OpenAI, Introducing GPT-5.4checked 2026-10-15; printed on 1 more page | Effort: xhigh |
| GPT-5.2OpenAI, released 2025-12-11 | 14.6% | OpenAI, Introducing GPT-5.2checked 2026-10-15; printed on 1 more page | Effort: xhigh; Tools: python |
| GPT-5.2 ProOpenAI, released 2025-12-11 | 31.3% | OpenAI, Introducing GPT-5.4checked 2026-10-15 | Effort: xhigh |
| GPT-5.1OpenAI, released 2025-11-12 | 12.5% | OpenAI, Introducing GPT-5.2checked 2026-10-15 | Effort: high; Tools: python |
| Claude Opus 4.7Anthropic, released 2026-04-16 | 22.9% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | - |
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 16.7% | OpenAI, Introducing GPT-5.5checked 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.