Model comparison
Gemini 3.1 Pro Preview vs GPT-5.3 Codex
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 45.8 on the Noometry Index.
Last verified . 8 shared benchmarks.
GoogleSummary
- They share 8 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 0 categories and GPT-5.3 Codex in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.3 Codex leads 48.0 to 37.7.
- The biggest single-benchmark swing is WeirdML: 72.1% for Gemini 3.1 Pro Preview and 79.3% for GPT-5.3 Codex.
- Gemini 3.1 Pro Preview is cheaper at $2 / $12 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 400K.
Side by side
| Gemini 3.1 Pro Preview | GPT-5.3 Codex | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 56.7 | 45.8 |
| Released | 2026-02-19 | 2026-02-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 66K | 128K |
| Input $ / M tokens | $2 | $1.75 |
| Output $ / M tokens | $12 | $14 |
| Results tracked | 71 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Codex leads
Gemini 3.1 Pro Preview: 42.5 (#99), GPT-5.3 Codex: 48.6 (#56)
| Benchmark | Gemini 3.1 Pro Preview | GPT-5.3 Codex |
|---|---|---|
| SWE-bench Verified | 75.6% | 74.8% |
| LMArena WebDev | 1447 | 1409 |
| WeirdML | 72.1% | 79.3% |
| ALE-Bench | 1,161 | 1,655 |
| DeepSWE | 11.7% | — |
| SciCode | 58.9% | — |
| GSO | 22.6% | — |
| LMArena Coding | 1484 | — |
| MirrorCode | 8.9% | — |
| AlgoTune | 2.02 | — |
Agentic & Tool Use GPT-5.3 Codex leads
Gemini 3.1 Pro Preview: 37.7 (#34), GPT-5.3 Codex: 48.0 (#9)
| Benchmark | Gemini 3.1 Pro Preview | GPT-5.3 Codex |
|---|---|---|
| Terminal-Bench | 80.2% | 78.4% |
| METR Time Horizons | 77% | 74.5% |
| Vending-Bench 2 | 3,774 | 5,940 |
| APEX-Agents | 35.3% | — |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
Reasoning Not comparable
Gemini 3.1 Pro Preview: 71.7 (#12), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Pro Preview | GPT-5.3 Codex |
|---|---|---|
| Epoch Capabilities Index | 154.77 | 156.77 |
| ARC-AGI-2 | 77.1% | — |
| SimpleBench | 79.6% | — |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| CritPt | 17.7% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| LMArena Hard Prompts | 1485 | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LMCA | 53.8% | — |
| ForecastBench | 59 | — |
Math Not comparable
Gemini 3.1 Pro Preview: 62.1 (#34), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Pro Preview | GPT-5.3 Codex |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 26% | — |
| LMArena Math | 1485 | — |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |
Knowledge Not comparable
Gemini 3.1 Pro Preview: 71.8 (#3), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Pro Preview | GPT-5.3 Codex |
|---|---|---|
| GPQA Diamond | 94.4% | — |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| Vectara Hallucination Rate | 10.4% | — |
| LMArena Expert | 1485 | — |
Multimodal Not comparable
Gemini 3.1 Pro Preview: 37.9 (#69), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Pro Preview | GPT-5.3 Codex |
|---|---|---|
| LMArena Vision | 1296 | — |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |
Multilingual Not comparable
Gemini 3.1 Pro Preview: 57.0 (#12), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Pro Preview | GPT-5.3 Codex |
|---|---|---|
| LMArena Non-English | 1477 | — |
| LMArena Chinese | 1529 | — |
| LMArena French | 1487 | — |
| LMArena German | 1491 | — |
| LMArena Japanese | 1493 | — |
| LMArena Korean | 1455 | — |
| LMArena Russian | 1498 | — |
| LMArena Spanish | 1479 | — |
Instruction Following Not comparable
Gemini 3.1 Pro Preview: 77.0 (#32), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Pro Preview | GPT-5.3 Codex |
|---|---|---|
| LMArena Instruction Following | 1466 | — |
Long Context Not comparable
Gemini 3.1 Pro Preview: 47.4 (#18), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Pro Preview | GPT-5.3 Codex |
|---|---|---|
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |
| LMArena Longer Query | 1483 | — |
Writing & Preference Not comparable
Gemini 3.1 Pro Preview: 66.1 (#37), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Pro Preview | GPT-5.3 Codex |
|---|---|---|
| LMArena Text | 1481 | — |
| LMArena Creative Writing | 1482 | — |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |
| LMArena Multi-Turn | 1488 | — |
Frequently asked questions
Is Gemini 3.1 Pro Preview better than GPT-5.3 Codex?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 45.8 on the Noometry Index.
Which is cheaper, Gemini 3.1 Pro Preview or GPT-5.3 Codex?
Gemini 3.1 Pro Preview is cheaper. It lists at $2 per million input tokens and $12 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.
Is Gemini 3.1 Pro Preview or GPT-5.3 Codex better for coding?
GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 42.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Pro Preview does, with 1.05M tokens against 400K.
How many benchmarks do Gemini 3.1 Pro Preview and GPT-5.3 Codex share?
8 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and GPT-5.3 Codex has 8.