← Back to leaderboard  ·  Show all task instances

multiprocessio/dsq

Commandline tool for running SQL queries against JSON, CSV, Excel, Parquet, and more.

3,867 go easy
542
Generated Behavioral Tests
91.0%
Best Score
Muse Spark 1.3 (max)

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 Muse Spark 1.3 (max) 91.0% $7.68 511 trace →
2 Claude Opus 5 (xhigh) 90.8% $41.46 268 trace →
3 Muse Spark 1.3 (xhigh) 84.5% $2.02 298 trace →
4 Claude Sonnet 4.6 80.3% $32.92 610 trace →
5 GPT 5.5 (xhigh) 79.3% $5.95 60 trace →
6 GPT-5.6 Sol (xhigh) 79.2% $7.37 48 trace →
7 Gemini 3.5 Flash 78.0% $8.37 231 trace →
8 Gemini 3.6 Flash 76.4% $2.98 143 trace →
9 Muse Spark 1.2 (xhigh) 76.4% $1.59 171 trace →
10 Claude Opus 4.6 76.4% $14.97 351 trace →
11 Claude Opus 4.8 (xhigh) 72.5% $11.09 104 trace →
12 GLM-5.2 71.0% $22.32 267 trace →
13 Claude Opus 4.7 (xhigh) 68.5% $6.13 105 trace →
14 Claude Opus 4.7 65.9% $3.28 98 trace →
15 GPT-5.6 Sol 64.9% $1.17 20 trace →
16 GPT 5.5 (high) 62.5% $2.97 44 trace →
17 GPT 5.5 54.2% $1.27 23 trace →
18 Gemini 3.1 Pro 50.6% $1.64 100 trace →
19 GPT 5.4 49.3% $0.54 24 trace →
20 Claude Haiku 4.5 30.3% $0.77 134 trace →
21 GPT 5 mini 25.3% $0.04 27 trace →
22 GPT 5.4 mini 10.1% $0.03 8 trace →
23 Gemini 3.7 Flash 8.3% $1.95 157 trace →
24 Muse Spark 1.1 (xhigh) 5.0% $1.02 246 trace →
25 Gemini 3 Flash 0.0% $0.38 118 trace →

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