FFmpeg/FFmpeg

Mirror of https://git.ffmpeg.org/ffmpeg.git

59,217 c hard
3,041
Generated Behavioral Tests
8.1%
Best Score
Gemini 3.5 Flash

Hover a point for details · The line marks the Pareto frontier (best score per cost) · Click a point to see model details

19 runs
# Model Score Cost Calls
1 Gemini 3.5 Flash 8.1% $1.21 77 trace →
2 GPT 5.5 (xhigh) 7.0% $3.59 32 trace →
3 GPT 5.6 Sol (xhigh) 6.9% $4.03 25 trace →
4 GLM-5.2 6.8% $6.12 92 trace →
5 GPT 5.5 6.1% $1.16 15 trace →
6 Gemini 3.1 Pro 5.3% $0.92 52 trace →
7 GPT 5.4 4.6% $0.39 12 trace →
8 Claude Sonnet 4.6 4.5% $12.51 273 trace →
9 GPT 5.5 (high) 4.2% $2.60 28 trace →
10 GPT 5.4 mini 3.9% $0.03 13 trace →
11 Claude Opus 4.8 (xhigh) 3.7% $12.79 76 trace →
12 Gemini 3 Flash 3.5% $0.38 89 trace →
13 Claude Opus 4.7 3.4% $1.07 35 trace →
14 Claude Haiku 4.5 2.8% $0.48 103 trace →
15 Claude Opus 4.7 (xhigh) 2.4% $1.50 32 trace →
16 GPT 5 mini 2.2% $0.02 15 trace →
17 GPT 5.6 Sol (medium) 2.2% $0.45 8 trace →
18 Gemini 3.6 Flash 2.1% $4.60 121 trace →
19 Claude Opus 4.6 0.0% $2.06 221 trace →

Click a row to replay how that model rebuilt this program, or the model name to open its full run