Sign in

Is Gemini 3.1 Pro SOTA in Coding › Agentic?#34 in Coding › AgenticRanked #34 in Coding › Agentic.

How it scores here

Gemini 3.1 Pro in Coding › Agentic

Primary benchmarks

  • Terminal-Bench 4.0: 2.7 (CI 105.0%–4.4) on Nov 18, 2026 (#40 of 44).

On the category's weighted score it is 90.7 points behind #1 Claude Opus 5.5 and 2.3 behind the next model up, Beam 1.0.

Nearby on the board

#ModelCategory score
31Minimax M316.3
32DeepSeek V4 Pro 081314.0
33Beam 1.011.6
34Gemini 3.1 Pro9.3
35GPT-5.4 Mini7.0
36Inkling Small4.7
37Nemotron 3.5 Super VL2.3
Standings

Coding › Agentic

#ModelState
1Claude Opus 5.5Co-SOTA
1Claude Sonnet 5.5Co-SOTA
1Kimi K3.1 ProCo-SOTA
2GPT-6.1 SolNear-SOTA
2GPT-6 AstraNear-SOTA
3Claude Fable 5.1Near-SOTA
4Gemini 4 Argon#4 in this category
5Claude Opus 5#5 in this category
6GPT-6.1 Terra#6 in this category
7GPT-6 Sol#7 in this category
8Muse Wonder#8 in this category
9Claude Fable 5#9 in this category

Category page →