← Back to leaderboard  ·  Show all task instances

jhspetersson/fselect

Find files with SQL-like queries

4,420 rs
3,115
Generated Behavioral Tests
87.0%
Best Score
Claude Opus 5 (xhigh)

Results by Model

Hover for details · Click a model to open it · Drag to zoom the x-axis · Shift-drag to pan · The line marks the Pareto frontier (best score per cost)

Per-Model Results

25 runs
# Model Score Cost Calls
1 Claude Opus 5 (xhigh) 87.0% $98.31 469 trace →
2 GPT 5.5 (xhigh) 76.4% $11.81 82 trace →
3 Muse Spark 1.3 (xhigh) 75.3% $1.20 188 trace →
4 GPT-5.6 Sol (xhigh) 75.1% $6.17 45 trace →
5 Claude Opus 4.8 (xhigh) 72.6% $22.17 208 trace →
6 GLM-5.2 71.0% $23.96 252 trace →
7 GPT 5.5 (high) 64.9% $3.56 39 trace →
8 GPT 5.5 57.3% $1.57 18 trace →
9 Muse Spark 1.2 (xhigh) 54.3% $2.70 254 trace →
10 Claude Opus 4.6 44.0% $9.78 262 trace →
11 Gemini 3.5 Flash 42.4% $9.72 275 trace →
12 GPT-5.6 Sol 39.9% $1.68 19 trace →
13 Claude Opus 4.7 29.3% $2.52 74 trace →
14 Gemini 3.1 Pro 24.1% $0.89 62 trace →
15 GPT 5.4 mini 20.3% $0.05 9 trace →
16 GPT 5.4 20.3% $0.43 12 trace →
17 Muse Spark 1.3 (max) 16.2% $5.51 354 trace →
18 Claude Haiku 4.5 9.9% $0.51 113 trace →
19 Gemini 3.6 Flash 6.2% $5.44 161 trace →
20 Claude Sonnet 4.6 2.1% $20.11 479 trace →
21 Gemini 3.7 Flash 1.7% $2.16 162 trace →
22 Muse Spark 1.1 (xhigh) 1.7% $1.23 190 trace →
23 Claude Opus 4.7 (xhigh) 1.4% $7.60 126 trace →
24 Gemini 3 Flash 0.9% $0.24 89 trace →
25 GPT 5 mini 0.0% $0.07 28 trace →

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