Skip to content

LLM Benchmark Hub

Model evidence, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Metrics
LLM Benchmark Hub
Loading data...

LLM Stats (DeepSWE) — leaderboard

Metric: Score (%). Source: llm-stats.com. 6 models tracked.

Top models

#ModelScore
1GPT-5.6 Sol72.7
2GPT-5.6 Terra69.6
3GPT-5.6 Luna67.2
4Grok 4.553
5GLM-5.246.2
6Seed 2.1 Pro32.7

Interactive version: aibenchmarks.dev/benchmark?slug=llm-stats-deepswe · How the rankings work · Data refreshed daily, snapshot 2026-07-13.