Leaderboard
Language ModelsProprietary
Gemini 3.1 Pro
Google's most capable Gemini (preview); tops several reasoning benchmarks.
Crosshair Index
75.9
#3 of 32 · Language Models
- Provider
- Google DeepMind
- Released
- 2026-02-19
- Parameters
- Undisclosed
- Context
- 1.048576M tokens
Token pricing
- Input
- $2 /1M
- Output
- $12 /1M
- Cache read
- $0.2 /1M
USD per 1M tokens · cache read = cached input (hit), cache write = caching surcharge · official list pricing (June 2026).
Industry skill web
Professional-domain strengths, composed from the benchmarks relevant to each field. Highlight an axis to see the benchmarks behind it.
Software Engineering
81
skill
Shipping working code against real repositories: bug fixes, feature patches, and competitive programming under tests.
Scorecard
| Benchmark | Score | Source | Status |
|---|---|---|---|
| GPQA Diamond Reasoning | 94.3%best | Google DeepMind — Gemini 3.1 Pro model cardvendor | unverified |
| Humanity's Last Exam Frontier | 44.4% | Google DeepMind — Gemini 3.1 Pro model cardvendor | unverified |
| SWE-bench Verified Agentic Coding | 80.6% | Google DeepMind — Gemini 3.1 Pro model cardvendor | unverified |
| LiveCodeBench Coding | — | not evaluated | |
| MMLU-Pro Knowledge | — | not evaluated | |
| LMArena Elo Human Preference | 1,488 | LMArena (arena.ai)3rd-party | unverified |
| AA Intelligence Index Composite | 57 | Artificial Analysis3rd-party | unverified |
| Corporate Finance Finance | 64.5% | Vals AI — CorpFin v23rd-party | unverified |
| LegalBench Law | 87.4%best | Vals AI — LegalBench3rd-party | unverified |
| TaxEval Tax & Accounting | 72.9% | Vals AI — TaxEval v23rd-party | unverified |
| Medical Coding Medicine | 59.1%best | Vals AI — MedCode3rd-party | unverified |