Model comparison
Gemini 3.5 Flash vs GPT-5.2 Codex
Gemini 3.5 Flash is the stronger model overall, scoring 54.1 to 42.2 on the Noometry Index.
Last verified . 2 shared benchmarks.
GoogleSummary
- They share 2 benchmarks with published results for both. Gemini 3.5 Flash scores higher in 1 category and GPT-5.2 Codex in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.2 Codex leads 40.7 to 24.8.
- Gemini 3.5 Flash is cheaper at $1.50 / $9 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
- Gemini 3.5 Flash accepts more context: 1.05M tokens versus 400K.
Side by side
| Gemini 3.5 Flash | GPT-5.2 Codex | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 54.1 | 42.2 |
| Released | 2026-05-19 | 2025-12-18 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 66K | 128K |
| Input $ / M tokens | $1.50 | $1.75 |
| Output $ / M tokens | $9 | $14 |
| Results tracked | 54 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.5 Flash leads
Gemini 3.5 Flash: 49.1 (#46), GPT-5.2 Codex: 45.4 (#66)
| Benchmark | Gemini 3.5 Flash | GPT-5.2 Codex |
|---|---|---|
| LMArena WebDev | 1499 | 1339 |
| ALE-Bench | 911.02 | 1,300 |
| SWE-bench Verified | 79.3% | — |
| DeepSWE | 37.4% | — |
| SWE-bench Verified (bash only) | — | 72.8% |
| SWE-bench Multilingual | — | 66.3% |
| SciCode | 53.1% | — |
| WeirdML | 62.6% | — |
| LMArena Coding | 1492 | — |
Agentic & Tool Use GPT-5.2 Codex leads
Gemini 3.5 Flash: 24.8 (#107), GPT-5.2 Codex: 40.7 (#20)
| Benchmark | Gemini 3.5 Flash | GPT-5.2 Codex |
|---|---|---|
| Terminal-Bench | — | 66.5% |
| APEX-Agents | 27.5% | — |
| GBAEval | 6.7% | — |
| GDP.pdf | 14% | — |
| Vending-Bench 2 | 5,396 | — |
Reasoning Not comparable
Gemini 3.5 Flash: 62.7 (#16), GPT-5.2 Codex: —
| Benchmark | Gemini 3.5 Flash | GPT-5.2 Codex |
|---|---|---|
| ARC-AGI-2 | 72.1% | — |
| SimpleBench | 76.7% | — |
| NYT Connections (extended) | 92.6% | — |
| ARC-AGI-1 | 92.5% | — |
| CritPt | 13.1% | — |
| Chess Puzzles | 50% | — |
| EnigmaEval | 25.4% | — |
| EBR-Bench | 4.8% | — |
| LMArena Hard Prompts | 1488 | — |
| Mystery Game Puzzles | 32% | — |
| DTBench | 94.7% | — |
| LMCA | 47.1% | — |
| Surface Evolver Bench | 58.1% | — |
| Epoch Capabilities Index | 154.55 | — |
| ForecastBench | 59 | — |
Math Not comparable
Gemini 3.5 Flash: 60.5 (#30), GPT-5.2 Codex: —
| Benchmark | Gemini 3.5 Flash | GPT-5.2 Codex |
|---|---|---|
| FrontierMath (Tiers 1-3) | 62.8% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.3% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 31% | — |
| LMArena Math | 1502 | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Not comparable
Gemini 3.5 Flash: 66.3 (#10), GPT-5.2 Codex: —
| Benchmark | Gemini 3.5 Flash | GPT-5.2 Codex |
|---|---|---|
| GPQA Diamond | 92.8% | — |
| SimpleQA Verified | 66.2% | — |
| LMArena Expert | 1493 | — |
Multimodal Not comparable
Gemini 3.5 Flash: 45.7 (#13), GPT-5.2 Codex: —
| Benchmark | Gemini 3.5 Flash | GPT-5.2 Codex |
|---|---|---|
| LMArena Vision | 1311 | — |
| Blueprint-Bench 2 | 33.6% | — |
| LMArena Document | 1463 | — |
Multilingual Not comparable
Gemini 3.5 Flash: 57.1 (#12), GPT-5.2 Codex: —
| Benchmark | Gemini 3.5 Flash | GPT-5.2 Codex |
|---|---|---|
| LMArena Non-English | 1475 | — |
| LMArena Chinese | 1525 | — |
| LMArena French | 1490 | — |
| LMArena German | 1500 | — |
| LMArena Japanese | 1481 | — |
| LMArena Korean | 1453 | — |
| LMArena Russian | 1491 | — |
| LMArena Spanish | 1478 | — |
Instruction Following Not comparable
Gemini 3.5 Flash: 77.2 (#29), GPT-5.2 Codex: —
| Benchmark | Gemini 3.5 Flash | GPT-5.2 Codex |
|---|---|---|
| LMArena Instruction Following | 1466 | — |
Long Context Not comparable
Gemini 3.5 Flash: 45.3 (#39), GPT-5.2 Codex: —
| Benchmark | Gemini 3.5 Flash | GPT-5.2 Codex |
|---|---|---|
| LMArena Longer Query | 1481 | — |
Writing & Preference Not comparable
Gemini 3.5 Flash: 65.5 (#46), GPT-5.2 Codex: —
| Benchmark | Gemini 3.5 Flash | GPT-5.2 Codex |
|---|---|---|
| LMArena Text | 1481 | — |
| LMArena Creative Writing | 1467 | — |
| EQ-Bench 4 | 1087 | — |
| LMArena Multi-Turn | 1482 | — |
Frequently asked questions
Is Gemini 3.5 Flash better than GPT-5.2 Codex?
Gemini 3.5 Flash is the stronger model overall, scoring 54.1 to 42.2 on the Noometry Index.
Which is cheaper, Gemini 3.5 Flash or GPT-5.2 Codex?
Gemini 3.5 Flash is cheaper. It lists at $1.50 per million input tokens and $9 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.
Is Gemini 3.5 Flash or GPT-5.2 Codex better for coding?
Gemini 3.5 Flash scores higher on coding benchmarks: 49.1 versus 45.4 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.5 Flash does, with 1.05M tokens against 400K.
How many benchmarks do Gemini 3.5 Flash and GPT-5.2 Codex share?
2 benchmarks have published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and GPT-5.2 Codex has 5.