Which model leads SWE-Perf?

Q: Which model leads SWE-Perf?

Gemini 3 Pro tops the board at 6.5

SWE-Perf Leaderboard — Model Scores

Pro Mode — raw scores, one benchmark under the lensthird-party eval harness

The field · 7 measured

0.96.5

7 models measured, most on the third-party eval harness. Gemini 3 Pro tops the board at 6.5.

7 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 7Bars show 0.9–6.5 · ◆ solid = first-party or better · outlined = arm's-length

01Gemini 3 ProGoogle6.5$2.0/M$12.0/M$1.077

02Claude Opus 4.5Anthropic4.7$5.0/M$25.0/M$3.191

03GPT-5.2OpenAI3.6$1.8/M$14.0/M$2.188

04MiniMax M2.1+1 altMiniMax3.1VENDOR$0.30/M$1.2/M$0.242

05Claude Sonnet 4.5Anthropic3$3.0/M$15.0/M$3.000

06MiniMax M2MiniMax1.4$0.30/M$1.2/M$0.536

07DeepSeek-V3.2DeepSeek0.9$0.28/M$0.42/M$0.389

◆ solid = independently verified · aggregator attested · vendor attributed — outlined = cross-reference · source-attributed. Dimmed ◆ = confidence inferred. “+N alts” = alternate disclosures in the drawer with why-demoted. Prices per million tokens; $/point = input price ÷ score. Every row opens its model dossier.

Verification: 7 models scored · 0 independently verified · 5 vendor cross-reference · 2 vendor-reported · 0 with source disagreement. How these tiers are assigned