Other · model
Flint benchmark scores
As of 2026-10-29, Flint (Other) has measured scores on 5 benchmarks and estimated scores on 18 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-SciCode | 45.6% | estimated ± 3.9 pp, high confidence |
| IFBench | 89.2% | measured |
| LiveCodeBench v6 | 80.3% | measured |
| SciCode | 45.3% | estimated ± 3.3 pp, high confidence |
| Terminal-Bench 2.1 | 54.9% | measured |
| IFEval | 95.1% | measured |
| AA Coding Index | 48.3% | estimated ± 5.3 pp, medium confidence |
| SWE-bench Verified | 74.2% | measured |
| SWE-bench Pro | 51.9% | estimated ± 4.6 pp, high confidence |
| AA-IFBench | 80.4% | estimated ± 7.4 pp, low confidence |
| AA Terminal-Bench 2.1 | 63.3% | estimated ± 6.8 pp, low confidence |
| Terminal-Bench 3.0 | 4.3% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 9.2% | estimated ± 2.7 pp, low confidence |
| Vals LiveCodeBench | 80.7% | estimated ± 2.0 pp, low confidence |
| Vals SWE-bench | 68.4% | estimated ± 6.8 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 48.4% | estimated ± 7.4 pp, medium confidence |
| AA Terminal-Bench 4.0 | 2.2% | estimated ± 11.6 pp, low confidence |
| DeepSWE | 33.2% | estimated ± 12.7 pp, low confidence |
| Vibe Code Bench | 2.1% | estimated ± 8.1 pp, medium confidence |
| NL2Repo | 29.5% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 73.1% | estimated ± 2.3 pp, medium confidence |
| SWE-Rebench | 57.1% | estimated ± 3.6 pp, medium confidence |
| LiveCodeBench | 75.7% | estimated ± 14.6 pp, low confidence |