Model comparison
Gemini 2.5 Flash vs GPT-5-Codex
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 37.9 on the Noometry Index.
Last verified . 3 shared benchmarks.
GoogleSummary
- They share 3 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 0 categories and GPT-5-Codex in 3 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5-Codex leads 30.9 to 18.1.
- The biggest single-benchmark swing is Terminal-Bench: 17.1% for Gemini 2.5 Flash and 44.3% for GPT-5-Codex.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 400K.
Side by side
| Gemini 2.5 Flash | GPT-5-Codex | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 39.3 | 37.9 |
| Released | 2025-04-17 | 2025-09-15 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.30 | $1.25 |
| Output $ / M tokens | $2.50 | $10 |
| Results tracked | 54 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5-Codex leads
Gemini 2.5 Flash: 35.8 (#220), GPT-5-Codex: 42.4 (#103)
| Benchmark | Gemini 2.5 Flash | GPT-5-Codex |
|---|---|---|
| WeirdML | 41.9% | 54.5% |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| LMArena Coding | 1424 | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Too close to call
Gemini 2.5 Flash: 30.8 (#74), GPT-5-Codex: 31.0 (#72)
| Benchmark | Gemini 2.5 Flash | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | 17.1% | 44.3% |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning GPT-5-Codex leads
Gemini 2.5 Flash: 18.1 (#286), GPT-5-Codex: 30.9 (#83)
| Benchmark | Gemini 2.5 Flash | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | 56.8% | 70.3% |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| ARC-AGI-1 | 33.3% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 2.7% | — |
| LMArena Hard Prompts | 1422 | — |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| Epoch Capabilities Index | 143.03 | — |
| ForecastBench | 60.6 | — |
Math Not comparable
Gemini 2.5 Flash: 39.9 (#98), GPT-5-Codex: —
| Benchmark | Gemini 2.5 Flash | GPT-5-Codex |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | — |
| Omni-MATH | 38.5% | — |
| LMArena Math | 1415 | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Not comparable
Gemini 2.5 Flash: 36.4 (#168), GPT-5-Codex: —
| Benchmark | Gemini 2.5 Flash | GPT-5-Codex |
|---|---|---|
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
| LMArena Expert | 1426 | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.8 (#32), GPT-5-Codex: —
| Benchmark | Gemini 2.5 Flash | GPT-5-Codex |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Not comparable
Gemini 2.5 Flash: 52.3 (#88), GPT-5-Codex: —
| Benchmark | Gemini 2.5 Flash | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1409 | — |
| LMArena Chinese | 1450 | — |
| LMArena French | 1433 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1385 | — |
| LMArena Russian | 1415 | — |
| LMArena Spanish | 1421 | — |
Instruction Following Not comparable
Gemini 2.5 Flash: 75.7 (#54), GPT-5-Codex: —
| Benchmark | Gemini 2.5 Flash | GPT-5-Codex |
|---|---|---|
| IFEval | 89.8% | — |
| LMArena Instruction Following | 1405 | — |
Long Context Not comparable
Gemini 2.5 Flash: 47.5 (#17), GPT-5-Codex: —
| Benchmark | Gemini 2.5 Flash | GPT-5-Codex |
|---|---|---|
| Fiction.LiveBench | 77.8% | — |
| LMArena Longer Query | 1419 | — |
Writing & Preference Not comparable
Gemini 2.5 Flash: 53.8 (#157), GPT-5-Codex: —
| Benchmark | Gemini 2.5 Flash | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1417 | — |
| LMArena Creative Writing | 1400 | — |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
| LMArena Multi-Turn | 1408 | — |
Frequently asked questions
Is Gemini 2.5 Flash better than GPT-5-Codex?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 37.9 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash or GPT-5-Codex?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; GPT-5-Codex lists at $1.25 and $10.
Is Gemini 2.5 Flash or GPT-5-Codex better for coding?
GPT-5-Codex scores higher on coding benchmarks: 42.4 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 400K.
How many benchmarks do Gemini 2.5 Flash and GPT-5-Codex share?
3 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and GPT-5-Codex has 3.