DForkTree Study - 128-Prompt Greedy AR - MBPP Function Alias: leaderboard
DForkTree v1 Table7,128promptsubset ofMBPP Function Alias,notfullbenchmark. Unchanged autoregressivenonthinkingBF16,Qwen3.5,SGLang0.5.22,RTX5090,batch1,temp0,max2048tokens. GSMlastnumber;MATHlastcompleteboxednormalized;HumanEvalofficialtests;MBPPfixedfunctionnamealiaswhenpromptomitsname. No copiedaccuracyunderdecoderchanges or throughputmetrics.
Metric: Score (%). Source: arxiv.org. Saturation forecast: Around February 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 9B | 68 | #803 |
| 2 | Qwen 3.5 4B | 65.6 | #1180 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=dforktree-study-128-prompt-greedy-ar-mbpp-function-alias · How It Works · Data refreshed daily, snapshot 2026-11-12.