Model comparison
Gemini 3 Pro vs GPT-5.1-Codex
Gemini 3 Pro is the stronger model overall, scoring 54.7 to 38.2 on the Noometry Index.
Last verified . 6 shared benchmarks.
GoogleSummary
- They share 6 benchmarks with published results for both. Gemini 3 Pro scores higher in 3 categories and GPT-5.1-Codex in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3 Pro leads 48.8 to 29.3.
- The biggest single-benchmark swing is ProofBench: 20% for Gemini 3 Pro and 9% for GPT-5.1-Codex.
Side by side
| Gemini 3 Pro | GPT-5.1-Codex | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 54.7 | 38.2 |
| Released | 2025-11-18 | 2025-11-12 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 67 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Pro leads
Gemini 3 Pro: 52.1 (#33), GPT-5.1-Codex: 41.7 (#107)
| Benchmark | Gemini 3 Pro | GPT-5.1-Codex |
|---|---|---|
| SWE-bench Verified (bash only) | 74.2% | 66% |
| LMArena WebDev | 1439 | 1337 |
| ALE-Bench | 1,177 | 1,245 |
| SWE-bench Verified | 72.9% | — |
| SWE-bench Multilingual | 68.7% | — |
| GSO | 18.6% | — |
| WeirdML | 69.9% | — |
| LMArena Coding | 1482 | — |
| AlgoTune | 1.83 | — |
Agentic & Tool Use Gemini 3 Pro leads
Gemini 3 Pro: 40.5 (#21), GPT-5.1-Codex: 37.8 (#32)
| Benchmark | Gemini 3 Pro | GPT-5.1-Codex |
|---|---|---|
| Terminal-Bench | 69.4% | 60.4% |
| METR Time Horizons | 71% | 70.8% |
| Berkeley Function Calling Leaderboard | 72.5% | — |
| GDPval | 40.3% | — |
| Remote Labor Index | 1.3% | — |
| τ²-bench Airline | 80.5% | — |
| τ²-bench Banking | 18% | — |
| τ²-bench Retail | 75.9% | — |
| τ²-bench Telecom | 91% | — |
| DeepResearch Bench | 46.3% | — |
| BALROG | 58.1% | — |
| LMArena Search | 1207 | — |
| Vending-Bench 2 | 5,478 | — |
Reasoning Not comparable
Gemini 3 Pro: 52.5 (#28), GPT-5.1-Codex: —
| Benchmark | Gemini 3 Pro | GPT-5.1-Codex |
|---|---|---|
| ARC-AGI-2 | 31.1% | — |
| SimpleBench | 76.4% | — |
| Kagi LLM Benchmark | 80.1% | — |
| NYT Connections (extended) | 94.4% | — |
| ARC-AGI-1 | 75% | — |
| CritPt | 6.9% | — |
| Chess Puzzles | 31% | — |
| EnigmaEval | 18.2% | — |
| LMArena Hard Prompts | 1481 | — |
| Epoch Capabilities Index | 152.96 | — |
| ForecastBench | 61.2 | — |
Math Gemini 3 Pro leads
Gemini 3 Pro: 48.8 (#50), GPT-5.1-Codex: 29.3 (#218)
| Benchmark | Gemini 3 Pro | GPT-5.1-Codex |
|---|---|---|
| ProofBench | 20% | 9% |
| MathArena Final-Answer Competitions | 67% | — |
| OTIS Mock AIME 2024-2025 | 91.4% | — |
| Omni-MATH | 55.5% | — |
| LMArena Math | 1475 | — |
| FrontierMath (Feb 2025 set) | 37.6% | — |
| FrontierMath Tier 4 (v1) | 18.8% | — |
Knowledge Not comparable
Gemini 3 Pro: 64.3 (#15), GPT-5.1-Codex: —
| Benchmark | Gemini 3 Pro | GPT-5.1-Codex |
|---|---|---|
| GPQA Diamond | 92.6% | — |
| Humanity's Last Exam | 37.5% | — |
| MMLU-Pro | 90.3% | — |
| Vectara Hallucination Rate | 13.6% | — |
| GPQA (HELM) | 80.3% | — |
| LMArena Expert | 1475 | — |
Multimodal Not comparable
Gemini 3 Pro: 56.9 (#1), GPT-5.1-Codex: —
| Benchmark | Gemini 3 Pro | GPT-5.1-Codex |
|---|---|---|
| LMArena Vision | 1305 | — |
| GeoBench | 84% | — |
| VPCT | 91% | — |
| LMArena Document | 1434 | — |
Multilingual Not comparable
Gemini 3 Pro: 57.1 (#14), GPT-5.1-Codex: —
| Benchmark | Gemini 3 Pro | GPT-5.1-Codex |
|---|---|---|
| LMArena Non-English | 1474 | — |
| LMArena Chinese | 1522 | — |
| LMArena French | 1492 | — |
| LMArena German | 1517 | — |
| LMArena Japanese | 1513 | — |
| LMArena Korean | 1449 | — |
| LMArena Russian | 1493 | — |
| LMArena Spanish | 1468 | — |
Instruction Following Not comparable
Gemini 3 Pro: 76.4 (#42), GPT-5.1-Codex: —
| Benchmark | Gemini 3 Pro | GPT-5.1-Codex |
|---|---|---|
| IFEval | 87.7% | — |
| LMArena Instruction Following | 1458 | — |
Long Context Not comparable
Gemini 3 Pro: 44.0 (#75), GPT-5.1-Codex: —
| Benchmark | Gemini 3 Pro | GPT-5.1-Codex |
|---|---|---|
| CL-bench | 15.8% | — |
| LMArena Longer Query | 1472 | — |
Writing & Preference Not comparable
Gemini 3 Pro: 66.6 (#34), GPT-5.1-Codex: —
| Benchmark | Gemini 3 Pro | GPT-5.1-Codex |
|---|---|---|
| LMArena Text | 1479 | — |
| LMArena Creative Writing | 1482 | — |
| EQ-Bench Creative Writing | 1525 | — |
| WildBench | 85.9% | — |
| LMArena Multi-Turn | 1484 | — |
Frequently asked questions
Is Gemini 3 Pro better than GPT-5.1-Codex?
Gemini 3 Pro is the stronger model overall, scoring 54.7 to 38.2 on the Noometry Index.
Is Gemini 3 Pro or GPT-5.1-Codex better for coding?
Gemini 3 Pro scores higher on coding benchmarks: 52.1 versus 41.7 in the Noometry coding category.
How many benchmarks do Gemini 3 Pro and GPT-5.1-Codex share?
6 benchmarks have published results for both models. Gemini 3 Pro has 67 scored results on Noometry and GPT-5.1-Codex has 6.