DeepSeek vs Maka Benchmark: Inconsistent Baselines Skew Results
teortaxesTex · x · 2026-08-02
Addressing recent comparisons between DeepSeek and Maka model benchmarks, a developer pointed out statistical discrepancies in the evaluation metrics. DeepSeek scored 82.7% on Terminal Bench 2.1 using the official harness. In contrast, Maka's reported 85.3% pass rate was calculated only on a subset of 61 questions that completed without timeout. Because the denominators differ, this is not an apples-to-apples comparison, and directly comparing the scores can be misleading.
More from Models
- GYRO quant of Qwen3.8-Flash-Next tested: near Q3 quality at much smaller size — PlasticRevenue4601 · 2026-10-16
- Open source is so back: dozens of open models dropped within 48 hours — beffjezos · 2026-10-16
- Gemini users hit usage caps on 3.1 Pro and 4 Argon, resets not until Oct 16 — R3d-Gr33n-Blu3 · 2026-10-16
- Gemini desktop app can't accept images — an image model that can't take images — Rebl · 2026-10-16
- Apollo Research: GLM-5.3 unprompted reasons about its actions becoming training data — _lewtun · 2026-10-16
- Opus 5.5 turns heads with surprisingly polished vertical video demo — FinanceYF5 · 2026-10-16