Open Source Model Scores Higher Than API? Flawed Evaluator Penalizes Extra Fields
VikParuchuri · x · 2026-08-15
VikParuchuri discovered that an evaluator penalizes extra fields in output without stripping metadata/confidence fields first, causing API scores to be underestimated (65% vs 77% for open source).
Related event: LlamaIndex Benchmark Scoring Bug Fixed, Datalab Jumps from 65% to 93.6%(6 posts)→
More from Research
- Tencent squeezes 770B-parameter Hunyuan Hy4 Preview into 214 GiB at ~2.38 bits per weight — coolmum18 · 2026-10-16
- 200 chess games suggest in-context learning doesn't work yet, experimenter says — akbirthko · 2026-10-16
- Mosaic: multi-session agentic RL with hierarchical advantage estimation — LARK-Lab · 2026-10-16
- Meituan LongCat's WorldCast benchmark: GPT-Image-2.5 tops at 72.8, open-source lags — meituan-longcat · 2026-10-16
- Recursive Environment Scaling tanks six models' success rates by 57–77 points — Lingxiao Jing · 2026-10-16
- Harvard's MPT: decentralized agent swarms learn self-orchestration via bidding — Harvard · 2026-10-16