# FrontierMath (legacy) leaderboard

Mathematics benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/math-frontier-math

FrontierMath legacy aggregate. Every model the catalog carries a published FrontierMath (legacy) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Mathematics |
| Measure | Open-ended mathematical reasoning with tool access |
| Tasks | Historical aggregate |
| Difficulty | Research-level mathematics |
| Published by | [FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI](https://epoch.ai/frontiermath) |

Legacy FrontierMath values retained for historical model pages. This field is not used in current rankings because it can mix prior benchmark versions and slices.

## FrontierMath (legacy) ranking

8 models with a published FrontierMath (legacy) value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Open-ended mathematical reasoning with tool access | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-5.6 Sol](https://modelchoice.dev/models/gpt-5-6-sol) | OpenAI | 89 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-5.6 Terra](https://modelchoice.dev/models/gpt-5-6-terra) | OpenAI | 84.9 | Observed 2026-11-21 · source benchlm:models |
| 3 | [GPT-5.6 Luna](https://modelchoice.dev/models/gpt-5-6-luna) | OpenAI | 78.6 | Observed 2026-11-21 · source benchlm:models |
| 4 | [GPT-5.5 Pro](https://modelchoice.dev/models/gpt-5-5-pro) | OpenAI | 52.4 | Observed 2026-11-21 · source benchlm:models |
| 5 | [GPT-5.5](https://modelchoice.dev/models/gpt-5-5) | OpenAI | 51.7 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-5.4 Pro](https://modelchoice.dev/models/gpt-5-4-pro) | OpenAI | 50 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Opus 4.7](https://modelchoice.dev/models/claude-opus-4-7) | Anthropic | 43.8 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Opus 4.7 (Adaptive)](https://modelchoice.dev/models/claude-opus-4-7-max) | Anthropic | 43.8 | Last good 2026-11-18 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
