← Back to leaderboard  ·  Show all task instances

HaliteChallenge/Halite

@twosigma's first artificial intelligence programming challenge

202 cpp medium
275
Generated Behavioral Tests
95.6%
Best Score
GPT 5.5 (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

24 runs
# Model Score Cost Calls
1 GPT 5.5 (xhigh) 95.6% $7.37 59 trace →
2 GPT-5.6 Sol (xhigh) 94.2% $6.43 47 trace →
3 GPT 5.5 (high) 93.1% $2.90 40 trace →
4 Claude Opus 5 (xhigh) 89.8% $42.45 238 trace →
5 Gemini 3.7 Flash 89.8% $2.11 139 trace →
6 Claude Opus 4.8 (xhigh) 84.4% $14.45 106 trace →
7 Gemini 3.6 Flash 84.0% $3.51 121 trace →
8 Claude Opus 4.6 80.4% $15.08 222 trace →
9 GPT 5.5 80.4% $1.06 17 trace →
10 Gemini 3.1 Pro 75.6% $1.56 73 trace →
11 Muse Spark 1.1 (xhigh) 72.0% $1.37 187 trace →
12 Claude Opus 4.7 71.6% $1.00 44 trace →
13 GPT-5.6 Sol 66.9% $0.70 13 trace →
14 GLM-5.2 58.2% $17.22 152 trace →
15 Gemini 3 Flash 47.3% $0.52 71 trace →
16 Claude Haiku 4.5 42.9% $0.45 106 trace →
17 Muse Spark 1.3 (max) 24.7% $8.46 326 trace →
18 Muse Spark 1.3 (xhigh) 24.0% $1.79 274 trace →
19 Claude Opus 4.7 (xhigh) 18.5% $3.13 72 trace →
20 Gemini 3.5 Flash 18.5% $5.29 172 trace →
21 GPT 5.4 18.5% $0.20 6 trace →
22 Claude Sonnet 4.6 14.2% $38.69 494 trace →
23 GPT 5 mini 1.5% $0.04 22 trace →
24 GPT 5.4 mini 0.0% $0.02 9 trace →

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