Benchmark
MRCR v2 · 1M Pointwise
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 10
- Scores recorded
- 18
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 43.3%
- Mean
- 26.6%
- Median
- 22.4%
- Std dev
- 22.1%
- 10th percentile
- 74%
- 90th percentile
- 12.3%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6<1M API-reproducible subset · 29 problems · max effort· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 77.8% |
| 2 | Claude Opus 4.6Anthropic Opus 4.6 launch page · adaptive thinking · max effort unless noted · 1M pointwise · 8-needle· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 76% |
| 3 | GPT 5.5xhigh · 1M window · 512K–1M bin · 8-needle · mean sequence-matcher ratio· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 74% |
| 4 | Claude Sonnet 4.6<1M API-reproducible subset · 54 problems · 64K extended thinking· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 71.3% |
| 5 | Claude Sonnet 4.61M bin · full internal set · adaptive thinking · max effort · 5 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 65.8% |
| 6 | Claude Sonnet 4.61M bin · full internal set · 64K extended thinking · 5 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 65.1% |
| 7 | Muse Spark 1.1Meta Model API · xhigh · 1M window · 512K–1M bin · 8-needle · mean sequence-matcher ratio· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 54.1% |
| 8 | Gemini 3.6 FlashGemini 3.6 Flash Model Card · July 2026 · 1M pointwise· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 54% |
| 9 | Gemini 3.5 FlashGemini 3.5 Flash Model Card · May 2026 · 1M pointwise· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.6% |
| 10 | Gemini 3.5 FlashGemini 3.6 Flash Model Card · July 2026 · 1M pointwise· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.6% |
| 11 | Gemini 3 Pro PreviewGemini 3 Pro Model Card · results as of November 2025 · 1M pointwise· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.3% |
| 12 | Gemini 3.1 Pro Preview1M pointwise· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.3% |
| 13 | Gemini 3.1 Pro PreviewGemini 3.5 Flash Model Card · May 2026 · 1M pointwise· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.3% |
| 14 | Gemini 3.1 Pro PreviewGemini 3.6 Flash Model Card · July 2026 · 1M pointwise· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.3% |
| 15 | Gemini 3.1 Pro Previewhigh · 1M window · 512K–1M bin · 8-needle · mean sequence-matcher ratio· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.3% |
| 16 | Gemini 3 Flash1M pointwise · 8-needle· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 22.1% |
| 17 | Gemini 3 FlashGemini 3.5 Flash Model Card · May 2026 · 1M pointwise· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 22.1% |
| 18 | Gemini 3.1 Flash LiteGemini 3.1 Flash-Lite Model Card · high thinking · default sampling · single attempt/pass@1 · 1M pointwise· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 12.3% |