BlogLLM Benchmark Scores as Published, Side by Side
BeyondAIME: Results as Published
Every result the catalog holds for BeyondAIME: 5 models from 4 developers, read from 1 page. 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 ByteDance-SeedIntroduced 2025Data version 2026103001, as of 2026-10-30
BeyondAIME is a 100-problem mathematics test released by ByteDance-Seed. The problems are drawn from high-school and university competitions and are written to be at least as hard as AIME problems 11 to 15. Each problem was revised by hand so it is not a copy of a public contest item, and the only answer is a positive integer. A response is scored by an exact match to that integer.
BeyondAIME
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Sonnet 4.6Anthropic, released 2026-02-17 | 47.3% | Mistral AI, Mistral Medium 3.5 model cardchecked 2026-10-15 | Effort: max |
| Claude Sonnet 4.5Anthropic, released 2025-09-29 | 59.8% | Mistral AI, Mistral Medium 3.5 model cardchecked 2026-10-15 | Effort: max |
| Qwen3.5-397B-A17BAlibaba, released 2026-02-16 | 72.3% | Mistral AI, Mistral Medium 3.5 model cardchecked 2026-10-15 | Effort: max |
| Kimi K2.5Moonshot AI, released 2026-01-27 | 60.3% | Mistral AI, Mistral Medium 3.5 model cardchecked 2026-10-15 | Effort: max |
| Mistral Medium 3.5Mistral AI, released 2026-05-22 | 66.9% | Mistral AI, Mistral Medium 3.5 model cardchecked 2026-10-15 | Effort: max |
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.