# FrontierMath Tier 4 (slim)

> FrontierMath Tier 4 results for 32 AI models we list, run by Epoch AI, with each result's setting, date and source.

- Full: https://www.anchorterminal.com/benchmarks/frontiermath-tier-4/index.md (~3,000 tokens) · this version ~2,930 tokens · JSON https://www.anchorterminal.com/benchmarks/frontiermath-tier-4/index.json · canonical https://www.anchorterminal.com/benchmarks/frontiermath-tier-4/
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-21
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

The hardest FrontierMath problems, an expansion set of 43 in version 2, each taking a specialist researcher days.

- Score: % of problems solved, higher is better
- Run by: Epoch AI
- Status: Current, newest result 19 November 2026
- Updated: as models are released
- Ceiling: The best result is within five points of a perfect score, so the test no longer tells the top models apart
- Data: https://epoch.ai/data/benchmark_data.zip (CC BY 4.0, https://epoch.ai/benchmarks/use-this-data), read 2026-11-20
- Method: https://epoch.ai/benchmarks/frontiermath-tier-4-v2

## Results: Tier 4 v2 (2026-06-12)

32 models we list, each at its best setting, best first.

| # | Model | Score | Range | Who ran it | Setting | Date | Source |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5.2](https://www.anchorterminal.com/tools/claude-fable-5-2.md) | 100.0% |  | Independent | effort max | 2026-11-06 | https://epoch.ai/benchmarks/use-this-data |
| 1 | [GPT-6.2 Astra](https://www.anchorterminal.com/tools/gpt-6-2-astra.md) | 100.0% |  | Independent | effort max | 2026-10-27 | https://epoch.ai/benchmarks/use-this-data |
| 1 | [GPT-6.1 Sol](https://www.anchorterminal.com/tools/openai-api.md) | 100.0% |  | Independent | effort max | 2026-09-29 | https://epoch.ai/benchmarks/use-this-data |
| 4 | [GPT-6 Astra](https://www.anchorterminal.com/tools/azure-openai.md) | 97.6% |  | Independent | effort high | 2026-08-30 | https://epoch.ai/benchmarks/use-this-data |
| 5 | [Gemini 4 Neon](https://www.anchorterminal.com/tools/gemini-4-neon.md) | 97.6% |  | Independent | effort xhigh | 2026-11-19 | https://epoch.ai/benchmarks/use-this-data |
| 6 | [Gemini 4 Carbon](https://www.anchorterminal.com/tools/gemini-4-carbon.md) | 95.1% |  | Independent | effort high | 2026-11-02 | https://epoch.ai/benchmarks/use-this-data |
| 7 | [Claude Opus 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 95.0% |  | Independent | effort max | 2026-09-22 | https://epoch.ai/benchmarks/use-this-data |
| 8 | [GPT-6.1 Terra](https://www.anchorterminal.com/tools/openai-api.md) | 92.7% |  | Independent | effort max | 2026-10-26 | https://epoch.ai/benchmarks/use-this-data |
| 9 | [GPT-6 Sol](https://www.anchorterminal.com/tools/azure-openai.md) | 90.0% |  | Independent | effort max | 2026-09-22 | https://epoch.ai/benchmarks/use-this-data |
| 10 | [Gemini 4 Hydrogen](https://www.anchorterminal.com/tools/gemini-4-hydrogen.md) | 87.8% |  | Independent | effort xhigh | 2026-11-13 | https://epoch.ai/benchmarks/use-this-data |
| 10 | [Claude Fable 5.1](https://www.anchorterminal.com/tools/anthropic-api.md) | 87.8% |  | Independent | effort max | 2026-09-01 | https://epoch.ai/benchmarks/use-this-data |
| 12 | [Claude Sonnet 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 80.5% |  | Independent | effort max | 2026-09-29 | https://epoch.ai/benchmarks/use-this-data |
| 13 | [Gemini 4 Argon](https://www.anchorterminal.com/tools/gemini-4-argon.md) | 78.0% |  | Independent | effort high | 2026-10-13 | https://epoch.ai/benchmarks/use-this-data |
| 14 | [Muse Wonder](https://www.anchorterminal.com/tools/meta-model-api.md) | 70.7% |  | Independent | effort max | 2026-10-12 | https://epoch.ai/benchmarks/use-this-data |
| 15 | [Kimi K3.1 Pro](https://www.anchorterminal.com/tools/kimi-k3-1-pro.md) | 65.8% |  | Independent | effort max | 2026-11-06 | https://epoch.ai/benchmarks/use-this-data |
| 16 | [GPT-6 Luna](https://www.anchorterminal.com/tools/azure-openai.md) | 56.1% |  | Independent | effort max | 2026-09-22 | https://epoch.ai/benchmarks/use-this-data |
| 17 | [DeepSeek V4.1 Flash](https://www.anchorterminal.com/tools/deepseek-v4-1-flash.md) | 46.3% |  | Independent | effort max | 2026-10-19 | https://epoch.ai/benchmarks/use-this-data |
| 17 | [Claude Haiku 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 46.3% |  | Independent | effort max | 2026-10-07 | https://epoch.ai/benchmarks/use-this-data |
| 17 | [Muse Spark 1.3](https://www.anchorterminal.com/tools/meta-model-api.md) | 46.3% |  | Independent | effort max | 2026-09-18 | https://epoch.ai/benchmarks/use-this-data |
| 20 | [Kimi K3](https://www.anchorterminal.com/tools/kimi-k3.md) | 39.0% |  | Independent | effort max | 2026-07-17 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FgZERSAQwxBAevQzBsWfUie.eval |
| 21 | [Muse Spark Open](https://www.anchorterminal.com/tools/muse-spark-open.md) | 31.7% |  | Independent | effort xhigh | 2026-10-15 | https://epoch.ai/benchmarks/use-this-data |
| 22 | [GLM-5.3](https://www.anchorterminal.com/tools/glm-5-3.md) | 29.3% |  | Independent | effort max | 2026-08-25 | https://epoch.ai/benchmarks/use-this-data |
| 23 | [Gemini 3.1 Pro (preview)](https://www.anchorterminal.com/tools/vertex-ai.md) | 26.8% |  | Independent |  | 2026-06-11 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FeXVWr3RBeSsWy5DAU8ed46.eval |
| 24 | [DeepSeek-V4-Flash-0731](https://www.anchorterminal.com/tools/deepseek-v4-flash-0731.md) | 24.4% |  | Independent | effort max | 2026-08-02 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FWYs83xB6NwrkMNyQJtuMcQ.eval |
| 25 | [Gemini 3.8 Flash](https://www.anchorterminal.com/tools/vertex-ai.md) | 21.9% |  | Independent | effort high | 2026-09-02 | https://epoch.ai/benchmarks/use-this-data |
| 26 | [Grok 4.7](https://www.anchorterminal.com/tools/xai-api.md) | 17.1% |  | Independent | effort xhigh | 2026-09-22 | https://epoch.ai/benchmarks/use-this-data |
| 26 | [GLM-5.3-Flash](https://www.anchorterminal.com/tools/glm-5-3-flash.md) | 17.1% |  | Independent | effort max | 2026-08-27 | https://epoch.ai/benchmarks/use-this-data |
| 26 | [Inkling-Small](https://www.anchorterminal.com/tools/inkling-small.md) | 17.1% |  | Independent | effort xhigh | 2026-08-14 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FDVD8G8DHNyzkowBzK7JvMt.eval |
| 29 | [Grok 4.3](https://www.anchorterminal.com/tools/xai-api.md) | 14.6% |  | Independent | effort high | 2026-06-17 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3iRQkf5v7Wu7YuZhxa76Gg.eval |
| 30 | [Inkling](https://www.anchorterminal.com/tools/inkling.md) | 4.9% |  | Independent | effort xhigh | 2026-08-06 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FjvJPoRYkPH9Sb5MX252oHp.eval |
| 31 | [DeepSeek V4 Pro](https://www.anchorterminal.com/tools/deepseek-api.md) | 2.4% |  | Independent | effort max | 2026-06-17 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FRAZ6VMfGtQSE8EvUZRRz4Q.eval |
| 32 | [Gemini 3.5 Flash-Lite](https://www.anchorterminal.com/tools/vertex-ai.md) | 0.0% |  | Independent | effort high | 2026-08-02 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FjuNVfKBcYTwaKnk9GRA2zL.eval |

Every setting, 39 rows:

| Model | As named | Score | Who ran it | Setting | Date |
| --- | --- | --- | --- | --- | --- |
| Claude Fable 5.2 | claude-fable-5-2 | 100.0% | Independent | effort max | 2026-11-06 |
| GPT-6.2 Astra | gpt-6.2-astra | 100.0% | Independent | effort max | 2026-10-27 |
| GPT-6.1 Sol | gpt-6.1-sol | 100.0% | Independent | effort max | 2026-09-29 |
| GPT-6 Astra | gpt-6-astra | 97.6% | Independent | effort high | 2026-08-30 |
| GPT-6 Astra | gpt-6-astra | 97.6% | Independent | effort max | 2026-08-30 |
| GPT-6 Astra | gpt-6-astra | 97.6% | Independent | effort xhigh | 2026-08-30 |
| Gemini 4 Neon | gemini-4-neon | 97.6% | Independent | effort xhigh | 2026-11-19 |
| GPT-6 Astra | gpt-6-astra | 97.6% | Independent | effort medium | 2026-08-30 |
| Gemini 4 Carbon | gemini-4-carbon | 95.1% | Independent | effort high | 2026-11-02 |
| Claude Opus 5.5 | claude-opus-5-5 | 95.0% | Independent | effort max | 2026-09-22 |
| GPT-6.1 Terra | gpt-6.1-terra | 92.7% | Independent | effort max | 2026-10-26 |
| GPT-6 Sol | gpt-6-sol | 90.0% | Independent | effort max | 2026-09-22 |
| Gemini 4 Hydrogen | gemini-4-hydrogen | 87.8% | Independent | effort xhigh | 2026-11-13 |
| Claude Fable 5.1 | claude-fable-5-1 | 87.8% | Independent | effort max | 2026-09-01 |
| GPT-6 Astra | gpt-6-astra | 87.8% | Independent | effort low | 2026-08-30 |
| GPT-6 Astra | gpt-6-astra | 82.9% | Independent | effort none | 2026-08-30 |
| Claude Sonnet 5.5 | claude-sonnet-5-5 | 80.5% | Independent | effort max | 2026-09-29 |
| Gemini 4 Argon | gemini-4-argon | 78.0% | Independent | effort high | 2026-10-13 |
| Muse Wonder | muse-wonder-1.0 | 70.7% | Independent | effort max | 2026-10-12 |
| Kimi K3.1 Pro | kimi-k3.1-pro-together | 65.8% | Independent | effort max | 2026-11-06 |
| GPT-6 Luna | gpt-6-luna | 56.1% | Independent | effort max | 2026-09-22 |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash-1017 | 46.3% | Independent | effort max | 2026-10-19 |
| Claude Haiku 5.5 | claude-haiku-5-5 | 46.3% | Independent | effort max | 2026-10-07 |
| Muse Spark 1.3 | muse-spark-1.3 | 46.3% | Independent | effort max | 2026-09-18 |
| Muse Spark 1.3 | muse-spark-1.3 | 41.5% | Independent | effort xhigh | 2026-09-16 |
| Kimi K3 | kimi-k3 | 39.0% | Independent | effort max | 2026-07-17 |
| Muse Spark Open | Muse-Spark-Open-816B-A42B | 31.7% | Independent | effort xhigh | 2026-10-15 |
| GLM-5.3 | glm-5.3 | 29.3% | Independent | effort max | 2026-08-25 |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | 26.8% | Independent | effort max | 2026-10-08 |
| Gemini 3.1 Pro (preview) | gemini-3.1-pro-preview | 26.8% | Independent |  | 2026-06-11 |
| DeepSeek-V4-Flash-0731 | deepseek-v4-flash-0731 | 24.4% | Independent | effort max | 2026-08-02 |
| Gemini 3.8 Flash | gemini-3.8-flash | 21.9% | Independent | effort high | 2026-09-02 |
| Grok 4.7 | grok-4.7 | 17.1% | Independent | effort xhigh | 2026-09-22 |
| GLM-5.3-Flash | glm-5.3-flash | 17.1% | Independent | effort max | 2026-08-27 |
| Inkling-Small | inkling-small | 17.1% | Independent | effort xhigh | 2026-08-14 |
| Grok 4.3 | grok-4.3 | 14.6% | Independent | effort high | 2026-06-17 |
| Inkling | Inkling | 4.9% | Independent | effort xhigh | 2026-08-06 |
| DeepSeek V4 Pro | deepseek-v4-pro | 2.4% | Independent | effort max | 2026-06-17 |
| Gemini 3.5 Flash-Lite | gemini-3.5-flash-lite | 0.0% | Independent | effort high | 2026-08-02 |

## Results: Tier 4 (2025-07-01)

1 model we list, each at its best setting, best first.

| # | Model | Score | Range | Who ran it | Setting | Date | Source |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | [Gemini 3.1 Pro (preview)](https://www.anchorterminal.com/tools/vertex-ai.md) | 16.7% |  | Independent |  | 2026-02-19 | https://epoch.ai/benchmarks/use-this-data |

A rank is among the models we list with a result, not a place on the whole leaderboard, and a model offered by several hosts is shown once, on its own listing.

Data: Epoch AI, Capabilities and benchmarking (CC BY 4.0), CC BY 4.0. All benchmarks: https://www.anchorterminal.com/benchmarks/index.md
