Benchmark
SWE-bench-Live MultiLang Java
Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.
- Models measured
- 9
- Scores recorded
- 23
- Sources
- 1
- IQ weight
- 1.14
Score distribution
- 37.4%
- Mean
- 37.1%
- Median
- 15.3%
- Std dev
- 22.6%
- 10th percentile
- 67%
- 90th percentile
- 16.1%
- Min
This benchmark has a weight of 1.14 for chat models, measured over 9 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: java, instances: 160, submitted: 2026-10-16· SWE-bench-Live leaderboard data | 68.1% |
| 2 | GPT-5.6 Solscaffold: slingshot-v3.4.0, set: java, instances: 160, submitted: 2026-10-08· SWE-bench-Live leaderboard data | 67.5% |
| 3 | Claude Opus 4.6scaffold: ami-agent, set: java, instances: 109, submitted: 2026-08-17· SWE-bench-Live leaderboard data | 67% |
| 4 | GPT-5.6 Solscaffold: slingshot-v3.3.0, set: java, instances: 160, submitted: 2026-09-01· SWE-bench-Live leaderboard data | 52.5% |
| 5 | GPT 5.5scaffold: swe-agent, set: java, instances: 102, submitted: 2026-06-05, effort: medium· SWE-bench-Live leaderboard data | 50% |
| 6 | GPT 5.5scaffold: openhands, set: java, instances: 102, submitted: 2026-06-05, effort: medium· SWE-bench-Live leaderboard data | 47.1% |
| 7 | GPT 5.5scaffold: claude-code, set: java, instances: 102, submitted: 2026-06-05, effort: medium· SWE-bench-Live leaderboard data | 45.1% |
| 8 | GPT 5.5scaffold: slingshot-v3.1.0, set: java, instances: 109, submitted: 2026-08-12, effort: medium· SWE-bench-Live leaderboard data | 41.3% |
| 9 | DeepSeek V4 Proscaffold: openhands, set: java, instances: 102, submitted: 2026-06-05· SWE-bench-Live leaderboard data | 39.2% |
| 10 | DeepSeek V4 Proscaffold: swe-agent, set: java, instances: 102, submitted: 2026-06-05· SWE-bench-Live leaderboard data | 39.2% |
| 11 | DeepSeek V4 Proscaffold: claude-code, set: java, instances: 102, submitted: 2026-06-05· SWE-bench-Live leaderboard data | 38.2% |
| 12 | GPT 5.2scaffold: claude-code, set: java, instances: 62, submitted: 2026-01-08, effort: medium, thinking· SWE-bench-Live leaderboard data | 37.1% |
| 13 | GPT 5.5scaffold: slingshot-v2.6.0, set: java, instances: 109, submitted: 2026-07-07, effort: medium· SWE-bench-Live leaderboard data | 36.7% |
| 14 | Claude Sonnet 4.5scaffold: claude-code, set: java, instances: 62, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 27.4% |
| 15 | DeepSeek V3.1 Terminusscaffold: swe-agent, set: java, instances: 62, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 27.4% |
| 16 | Gemini 3 Flashscaffold: swe-agent, set: java, instances: 62, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 25.8% |
| 17 | DeepSeek V3.1 Terminusscaffold: openhands, set: java, instances: 62, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 24.2% |
| 18 | Gemini 3 Flashscaffold: openhands, set: java, instances: 62, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 24.2% |
| 19 | DeepSeek V3.1 Terminusscaffold: claude-code, set: java, instances: 62, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 22.6% |
| 20 | GPT 5.2scaffold: openhands, set: java, instances: 62, submitted: 2026-01-08, effort: medium, thinking· SWE-bench-Live leaderboard data | 22.6% |
| 21 | GPT 5.2scaffold: swe-agent, set: java, instances: 62, submitted: 2026-01-08, effort: medium, thinking· SWE-bench-Live leaderboard data | 22.6% |
| 22 | Claude Sonnet 4.5scaffold: openhands, set: java, instances: 62, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 19.4% |
| 23 | Claude Sonnet 4.5scaffold: swe-agent, set: java, instances: 62, submitted: 2026-01-08· SWE-bench-Live leaderboard data | 16.1% |