# MirrorCode

> MirrorCode results for 19 AI models we list, run by Epoch AI, with each result's setting, date and source.

- Canonical: https://www.anchorterminal.com/benchmarks/mirrorcode/
- Markdown: https://www.anchorterminal.com/benchmarks/mirrorcode/index.md (~2,100 tokens)
- Slim: https://www.anchorterminal.com/benchmarks/mirrorcode/index.min.md (~1,980 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/benchmarks/mirrorcode/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-21

An agent rebuilds a whole program from its behaviour alone, without the source or the internet, and must match the original's output on held-out end-to-end tests. Epoch AI and METR built it; the leaderboard runs 15 medium and large programs in two languages, three attempts each, with up to 10 billion tokens and 7 days an attempt.

- Score: % of tasks solved, higher is better
- Run by: Epoch AI
- Status: Current, newest result 17 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/MirrorCode

## Results

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

| # | Model | Score | Range | Who ran it | Setting | Date | Source |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | [Claude Sonnet 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 97.8% |  | Independent | effort max | 2026-10-05 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FUTD5SC5v2BgiwNauF9YrFo.eval |
| 2 | [Claude Opus 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 95.6% |  | Independent | effort max | 2026-10-30 | https://epoch.ai/benchmarks/use-this-data |
| 3 | [Claude Fable 5.1](https://www.anchorterminal.com/tools/anthropic-api.md) | 93.3% |  | Independent | effort max | 2026-09-09 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fj3QzF2QVnNghvyFneqEuiu.eval |
| 4 | [Claude Haiku 5.5](https://www.anchorterminal.com/tools/anthropic-api.md) | 78.9% |  | Independent | effort max | 2026-10-21 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FifSAAMJA9S73m6pAyRWxUD.eval |
| 5 | [GPT-6.1 Terra](https://www.anchorterminal.com/tools/openai-api.md) | 76.7% |  | Independent | effort max | 2026-10-30 | https://epoch.ai/benchmarks/use-this-data |
| 6 | [GPT-6.2 Astra](https://www.anchorterminal.com/tools/gpt-6-2-astra.md) | 67.8% |  | Independent | effort max | 2026-10-27 | https://epoch.ai/benchmarks/use-this-data |
| 7 | [DeepSeek V4.1 Flash](https://www.anchorterminal.com/tools/deepseek-v4-1-flash.md) | 64.4% |  | Independent | effort max | 2026-10-21 | https://epoch.ai/benchmarks/use-this-data |
| 8 | [GPT-6.1 Sol](https://www.anchorterminal.com/tools/openai-api.md) | 61.1% |  | Independent | effort max | 2026-10-05 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FjGPEpcBgJ4gakLdxgAqbR8.eval |
| 9 | [GPT-6 Astra](https://www.anchorterminal.com/tools/azure-openai.md) | 60.0% |  | Independent | effort max | 2026-10-29 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FFGZUtmNQZpZtk8ft5uCJkA.eval |
| 10 | [Gemini 4 Argon](https://www.anchorterminal.com/tools/gemini-4-argon.md) | 58.9% |  | Independent | effort high | 2026-10-14 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fh7xMzFUTMGSGqUSKUpxkUW.eval |
| 11 | [Grok 4.7](https://www.anchorterminal.com/tools/xai-api.md) | 54.4% |  | Independent | effort xhigh | 2026-10-29 | https://epoch.ai/benchmarks/use-this-data |
| 11 | [Muse Spark 1.3](https://www.anchorterminal.com/tools/meta-model-api.md) | 54.4% |  | Independent | effort max | 2026-10-20 | https://epoch.ai/benchmarks/use-this-data |
| 11 | [Kimi K3](https://www.anchorterminal.com/tools/kimi-k3.md) | 54.4% |  | Independent | effort max | 2026-09-03 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FbeEmcaWF8wxsWTLD5bMYxi.eval |
| 14 | [GPT-6 Sol](https://www.anchorterminal.com/tools/azure-openai.md) | 48.9% |  | Independent | effort max | 2026-10-29 | https://epoch.ai/benchmarks/use-this-data |
| 15 | [Muse Wonder](https://www.anchorterminal.com/tools/meta-model-api.md) | 45.6% |  | Independent | effort max | 2026-10-14 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4SF6nvuJows76zkypDWF3b.eval |
| 16 | [Kimi K3.1 Pro](https://www.anchorterminal.com/tools/kimi-k3-1-pro.md) | 43.3% |  | Independent | effort max | 2026-11-17 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FS2mVtBattZSe5WZPkXNicA.eval |
| 17 | [Gemini 3.8 Flash](https://www.anchorterminal.com/tools/vertex-ai.md) | 38.9% |  | Independent | effort high | 2026-09-02 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FFi32v8c7rD82qhgYVcsz7g.eval |
| 18 | [GPT-6 Luna](https://www.anchorterminal.com/tools/azure-openai.md) | 26.7% |  | Independent | effort max | 2026-10-21 | https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FWQ4gVVhGBfWoRkRwUvNYgs.eval |
| 19 | [Gemini 3.1 Pro (preview)](https://www.anchorterminal.com/tools/vertex-ai.md) | 8.9% |  | Independent | effort high | 2026-08-10 | https://epoch.ai/benchmarks/use-this-data |

Every setting, 22 rows:

| Model | As named | Score | Who ran it | Setting | Date |
| --- | --- | --- | --- | --- | --- |
| Claude Sonnet 5.5 | claude-sonnet-5-5 | 97.8% | Independent | effort max | 2026-10-05 |
| Claude Opus 5.5 | claude-opus-5-5 | 95.6% | Independent | effort max | 2026-10-30 |
| Claude Fable 5.1 | claude-fable-5-1 | 93.3% | Independent | effort max | 2026-09-09 |
| Claude Haiku 5.5 | claude-haiku-5-5 | 78.9% | Independent | effort max | 2026-10-21 |
| Claude Opus 5.5 | claude-opus-5-5 | 78.9% | Independent | effort high | 2026-09-22 |
| GPT-6.1 Terra | gpt-6.1-terra | 76.7% | Independent | effort max | 2026-10-30 |
| Claude Fable 5.1 | claude-fable-5-1 | 73.3% | Independent | effort high | 2026-09-10 |
| GPT-6.2 Astra | gpt-6.2-astra | 67.8% | Independent | effort max | 2026-10-27 |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | 64.4% | Independent | effort max | 2026-10-21 |
| GPT-6.1 Sol | gpt-6.1-sol | 61.1% | Independent | effort max | 2026-10-05 |
| GPT-6 Astra | gpt-6-astra | 60.0% | Independent | effort max | 2026-10-29 |
| Gemini 4 Argon | gemini-4-argon | 58.9% | Independent | effort high | 2026-10-14 |
| Grok 4.7 | grok-4.7 | 54.4% | Independent | effort xhigh | 2026-10-29 |
| Muse Spark 1.3 | muse-spark-1.3 | 54.4% | Independent | effort max | 2026-10-20 |
| Kimi K3 | kimi-k3 | 54.4% | Independent | effort max | 2026-09-03 |
| GPT-6 Sol | gpt-6-sol | 48.9% | Independent | effort max | 2026-10-29 |
| GPT-6 Astra | gpt-6-astra | 46.7% | Independent | effort high | 2026-08-30 |
| Muse Wonder | muse-wonder-1.0 | 45.6% | Independent | effort max | 2026-10-14 |
| Kimi K3.1 Pro | kimi-k3.1-pro-together | 43.3% | Independent | effort max | 2026-11-17 |
| Gemini 3.8 Flash | gemini-3.8-flash | 38.9% | Independent | effort high | 2026-09-02 |
| GPT-6 Luna | gpt-6-luna | 26.7% | Independent | effort max | 2026-10-21 |
| Gemini 3.1 Pro (preview) | gemini-3.1-pro-preview | 8.9% | Independent | effort high | 2026-08-10 |

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. These results don't move our grades.

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

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
