← Back to leaderboard  ·  Show all task instances

Esubaalew/run

Universal multi-language runner and smart REPL written in Rust.

919 rs medium
1,212
Generated Behavioral Tests
92.8%
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) 92.8% $45.41 334 trace →
2 GLM-5.2 88.2% $36.85 234 trace →
3 Claude Opus 4.7 (xhigh) 88.0% $19.96 282 trace →
4 Claude Opus 4.8 (xhigh) 86.5% $14.03 122 trace →
5 Claude Opus 4.6 85.2% $14.72 342 trace →
6 Claude Sonnet 4.6 85.2% $32.29 669 trace →
7 GPT 5.5 (xhigh) 84.5% $6.28 78 trace →
8 Muse Spark 1.2 (xhigh) 82.4% $0.17 143 trace →
9 GPT-5.6 Sol 81.3% $0.76 11 trace →
10 GPT 5.5 (high) 80.6% $3.33 44 trace →
11 Muse Spark 1.1 (xhigh) 80.0% $0.24 98 trace →
12 Claude Opus 4.7 73.2% $1.91 73 trace →
13 GPT 5.5 72.7% $0.82 14 trace →
14 Muse Spark 1.3 (max) 70.4% $9.18 323 trace →
15 GPT 5.4 70.1% $0.21 11 trace →
16 Muse Spark 1.3 (xhigh) 69.0% $1.95 255 trace →
17 GPT-5.6 Sol (xhigh) 67.7% $5.47 39 trace →
18 Gemini 3.7 Flash 64.7% $1.88 119 trace →
19 Gemini 3.6 Flash 63.5% $2.98 105 trace →
20 Gemini 3.5 Flash 59.7% $4.26 156 trace →
21 Gemini 3.1 Pro 58.5% $3.42 156 trace →
22 Gemini 3 Flash 54.5% $0.26 85 trace →
23 Claude Haiku 4.5 42.3% $0.32 104 trace →
24 GPT 5.4 mini 37.6% $0.03 18 trace →
25 GPT 5 mini 1.6% $0.03 16 trace →

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