Benchmark
SWE-bench-Live MultiLang Rust
Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.
- Models measured
- 8
- Scores recorded
- 19
- Sources
- 1
- IQ weight
- 0.93
Score distribution
- 31.4%
- Mean
- 28.9%
- Median
- 7.8%
- Std dev
- 26.7%
- 10th percentile
- 37.8%
- 90th percentile
- 17.8%
- Min
This benchmark has a weight of 0.93 for chat models, measured over 8 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4.1 Flashscaffold: tianxicode, set: rust, instances: 171, submitted: 2026-10-20· SWE-bench-Live leaderboard data | 50.9% |
| 2 | Claude Opus 4.6scaffold: ami-agent, set: rust, instances: 94, submitted: 2026-06-25· SWE-bench-Live leaderboard data | 48.9% |
| 3 | Gemini 3 Flashscaffold: swe-agent, set: rust, instances: 45, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 37.8% |
| 4 | Gemini 3 Flashscaffold: openhands, set: rust, instances: 45, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 35.6% |
| 5 | DeepSeek V4 Proscaffold: swe-agent, set: rust, instances: 64, submitted: 2026-06-05· SWE-bench-Live leaderboard data | 34.4% |
| 6 | GPT 5.2scaffold: claude-code, set: rust, instances: 45, submitted: 2026-01-08, effort: medium, thinking· SWE-bench-Live leaderboard data | 33.3% |
| 7 | GPT 5.5scaffold: claude-code, set: rust, instances: 64, submitted: 2026-06-05, effort: medium· SWE-bench-Live leaderboard data | 32.8% |
| 8 | DeepSeek V4 Proscaffold: claude-code, set: rust, instances: 64, submitted: 2026-06-05· SWE-bench-Live leaderboard data | 29.7% |
| 9 | GPT 5.5scaffold: openhands, set: rust, instances: 64, submitted: 2026-06-05, effort: medium· SWE-bench-Live leaderboard data | 29.7% |
| 10 | Claude Sonnet 4.5scaffold: swe-agent, set: rust, instances: 45, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 28.9% |
| 11 | DeepSeek V3.1 Terminusscaffold: swe-agent, set: rust, instances: 45, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 28.9% |
| 12 | GPT 5.2scaffold: swe-agent, set: rust, instances: 45, submitted: 2026-01-08, effort: medium, thinking· SWE-bench-Live leaderboard data | 28.9% |
| 13 | DeepSeek V4 Proscaffold: openhands, set: rust, instances: 64, submitted: 2026-06-05· SWE-bench-Live leaderboard data | 28.1% |
| 14 | GPT 5.5scaffold: swe-agent, set: rust, instances: 64, submitted: 2026-06-05, effort: medium· SWE-bench-Live leaderboard data | 28.1% |
| 15 | Claude Sonnet 4.5scaffold: openhands, set: rust, instances: 45, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 26.7% |
| 16 | DeepSeek V3.1 Terminusscaffold: openhands, set: rust, instances: 45, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 26.7% |
| 17 | GPT 5.2scaffold: openhands, set: rust, instances: 45, submitted: 2026-01-08, effort: medium, thinking· SWE-bench-Live leaderboard data | 26.7% |
| 18 | Claude Sonnet 4.5scaffold: claude-code, set: rust, instances: 45, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 22.2% |
| 19 | DeepSeek V3.1 Terminusscaffold: claude-code, set: rust, instances: 45, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 17.8% |