Skip to main content
CodeLint.Dev Dev Tools

LLM Benchmark Leaderboard

Benchmark scores for 11 major language models, compiled July 2026 from public leaderboards and vendor announcements. Blank cells mean no published score — scores are never estimated. Sortable by provider and evaluation metric.

Score colours: ≥ 90 excellent 75 – 89 good < 75 below avg — not reported
11 models
Model Params SWE-bench V SWE-bench Pro GPQA-D OSWorld Terminal-Bench ARC-AGI-2 Context Notes
Claude Fable 5
Anthropic · 2026
Unknown95.01MAnthropic premium tier — leads SWE-bench Verified among generally available models
GPT-5.5
OpenAI · 2026
Unknown88.793.61MSWE-bench Verified score is vendor-reported
Claude Opus 4.8
Anthropic · 2026
Unknown88.669.293.61MLeads SWE-bench Pro among active models
Claude Sonnet 5
Anthropic · 2026-06
Unknown82.163.296.288.384.71MGPQA Diamond record holder (96.2%) at mid-tier pricing
Gemini 3.1 Pro
Google · 2026
Unknown80.694.377.11MStrong multimodal reasoning; video input
DeepSeek V4 Flash
DeepSeek · 2026-04
284B MoE (13B active)73.786.01MOpen weights (MIT); 79.0% SWE-bench Verified at max reasoning effort
DeepSeek V4 Pro
DeepSeek · 2026-04
1.6T MoE (49B active)73.61MOpen weights (MIT); 80.6% SWE-bench Verified at max reasoning effort
Claude Haiku 4.5
Anthropic · 2025-10
Unknown73.3200KFastest and cheapest Claude
o3
OpenAI · 2025-04
Unknown69.183.3200KScores from OpenAI's April 2025 announcement
GPT-5.4
OpenAI · 2026
Unknown75.01MValue flagship with tool search
Gemini 3.5 Flash
Google · 2026
Unknown55.176.21MAgentic coding at fast-tier pricing

Data as of May 2025. Scores may vary by source, prompt format, and evaluation methodology. Always verify against primary sources.