Skip to content

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
25.3%69.9%
The band covers the middle 80% of scores. The line marks the median.

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 systemScore
1Claude Fable 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.9%
2GPT-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%
3Claude Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.3%
4Claude 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%
5Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.9%
6Claude 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%
7Gemini 4 Carbon· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.2%
8Claude 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%
9Claude 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%
10Gemini 4 Argon· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55%
11Claude 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%
12Claude Haiku 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim43.8%
13Claude 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%
14GPT-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%
15GPT-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%
16GPT-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%
17Grok 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim29%
18Grok 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%
19Kimi 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 systemScore
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