Benchmark
FrontierSWE v2
Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.
- Models and systems measured
- 13
- Scores recorded
- 20
- Sources
- 2
- IQ weight
- 1.30
Score distribution
- 47.7%
- Mean
- 55%
- Median
- 14.9%
- Std dev
- 29%
- 10th percentile
- 62.3%
- 90th percentile
- 25.3%
- Min
This benchmark has a weight of 1.30 for chat models, measured over 12 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 1 | Claude Fable 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 69.9% |
| 2 | GPT-6 AstraOpus 5.5 System Card capability section· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 65.5% |
| 3 | Claude Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 62.3% |
| 4 | Claude Opus 5.5Opus 5.5 System Card capability section· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 62.3% |
| 5 | Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 61.9% |
| 6 | Claude Sonnet 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · Proximus harness · max · 34 tasks · mean@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 61.9% |
| 7 | Gemini 4 Carbon· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 61.2% |
| 8 | Claude Fable 5.1Opus 5.5 System Card capability section· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 56.3% |
| 9 | Claude Fable 5.1Proximal Proximus harness · mean@5 · max effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 56.3% |
| 10 | Gemini 4 Argon· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 55% |
| 11 | Claude Fable 5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · Proximal public result · max · mean@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 47% |
| 12 | Claude Haiku 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 43.8% |
| 13 | Claude Haiku 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · Proximus harness · max · 34 tasks · mean@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 43.8% |
| 14 | GPT-5.6 Soladaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · Proximal public result · max · mean@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 32.2% |
| 15 | GPT-5.6 SolOpus 5.5 System Card capability section· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 32.2% |
| 16 | GPT-5.6 SolProximal Proximus harness · mean@5 · max effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 32.2% |
| 17 | Grok 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 29% |
| 18 | Grok 4.7Proximal Proximus harness · mean@5 · xhigh effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 29% |
| 19 | Kimi K3Proximal Proximus harness · mean@5 · max effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 25.9% |
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| Grok 4.6Proximal Proximus harness · mean@5 · xhigh effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 25.3% |
Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats