Skip to main content

Claude 3.7 Sonnet vs GPT-5 mini

SpecClaude 3.7 SonnetGPT-5 mini
Respan Index19.3 (#131)20.0 (#129)
Blended price per 1M-$0.688
Context window200K400K
Input / output per 1M-$0.25 / $2
Max output128K128K
Inputtext, visiontext, vision
Released2025-02-242025-08-07

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryClaude 3.7 SonnetGPT-5 mini
Coding7.3 Claude 3.7 Sonnet9.1 GPT-5 mini
Agents13.9 Claude 3.7 Sonnet4.4 GPT-5 mini
Reasoning23.1 Claude 3.7 Sonnet31.5 GPT-5 mini
Knowledge & language15.7* Claude 3.7 Sonnet21.6 GPT-5 mini
Human preference44.1 Claude 3.7 Sonnet43.9 GPT-5 mini

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

GPT-5 mini leads on 7 of the 8 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkClaude 3.7 SonnetGPT-5 mini
LMArena Elo13881390
LMArena Vision (LMArena)11931185
GPQA Diamond79.7%81.6%
MATH Level 5 (Epoch AI)91.2%97.8%
OTIS Mock AIME 2024-2025 (Epoch AI)57.8%86.7%
SWE-bench Verified (Epoch AI)61%64.7%
AIME 202549.2%87.5%
SWE-bench Verified70.3%71%

FAQ

Is Claude 3.7 Sonnet better than GPT-5 mini?

GPT-5 mini scores 20.0 on the Respan Index (#129), ahead of Claude 3.7 Sonnet at 19.3 (#131). GPT-5 mini leads on 7 of the 8 benchmarks both report.

Which has the larger context window?

Claude 3.7 Sonnet accepts 200K tokens and GPT-5 mini 400K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.