GLM-5.3 coding post-training run jumps Terminal-Bench4 from 34.8% to 56.1%
echen · x · 2026-11-13
A new coding post-training run on GLM-5.3 shows large gains across coding benchmarks:
- Terminal-Bench4: 34.8% → 56.1% (+21.3pp)
- SWE-marathon: 30% → 45% pass@1 (+15.0pp)
- sudo L7: 14.5% → 28.9% (+14.4pp)
- DeepSWE: 66.90% → 73.45% (+6.5pp)
More from Models
- Qwen3.8-27B quantized to run on 12GB RAM; router claims 97.5% of Opus 5.5 at 1/10 cost — Saul_Loveman · 2026-11-13
- Gemini 4 Carbon keeps saying 'we' instead of 'I' on PostTrainBench — maksym_andr · 2026-11-13
- Inkling 2 Small loses 9 Pokemon battles to learn the opponent's strategy, then wins on the 10th try — simonguozirui · 2026-11-13
- Paying Google to use its models is still surprisingly hard, dev says — xeophon · 2026-11-13
- A developer's personal coding benchmark ranks 19 models on 21 tasks — teortaxesTex · 2026-11-13
- LLMs' mental map of SF tested: best street-level score 0.32 vs 0.23 random — Evening_Hawk_7470 · 2026-11-13