Model comparison
Gemini 3.1 Flash Lite vs GPT-5.3 Codex
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 8.6× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
GoogleSummary
- They share 4 benchmarks with published results for both. Gemini 3.1 Flash Lite 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 30.2.
- The biggest single-benchmark swing is WeirdML: 52.2% for Gemini 3.1 Flash Lite and 79.3% for GPT-5.3 Codex.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 400K.
Side by side
| Gemini 3.1 Flash Lite | GPT-5.3 Codex | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 40.8 | 45.8 |
| Released | 2026-03-03 | 2026-02-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.25 | $1.75 |
| Output $ / M tokens | $1.50 | $14 |
| Results tracked | 38 | 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 Flash Lite: 37.8 (#188), GPT-5.3 Codex: 48.6 (#56)
| Benchmark | Gemini 3.1 Flash Lite | GPT-5.3 Codex |
|---|---|---|
| LMArena WebDev | 1256 | 1409 |
| WeirdML | 52.2% | 79.3% |
| ALE-Bench | 797.73 | 1,655 |
| SWE-bench Verified | — | 74.8% |
| SciCode | 41.9% | — |
| LMArena Coding | 1400 | — |
Agentic & Tool Use GPT-5.3 Codex leads
Gemini 3.1 Flash Lite: 30.2 (#79), GPT-5.3 Codex: 48.0 (#9)
| Benchmark | Gemini 3.1 Flash Lite | GPT-5.3 Codex |
|---|---|---|
| Terminal-Bench | — | 78.4% |
| DeepResearch Bench | 37.3% | — |
| METR Time Horizons | — | 74.5% |
| Vending-Bench 2 | — | 5,940 |
Reasoning Not comparable
Gemini 3.1 Flash Lite: 22.9 (#186), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Flash Lite | GPT-5.3 Codex |
|---|---|---|
| Epoch Capabilities Index | 144.47 | 156.77 |
| Kagi LLM Benchmark | 67.2% | — |
| NYT Connections (extended) | 8.2% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 25% | — |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| LMArena Hard Prompts | 1407 | — |
| DTBench | 76.8% | — |
| LMCA | 35% | — |
| ForecastBench | 54.4 | — |
Math Not comparable
Gemini 3.1 Flash Lite: 40.7 (#90), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Flash Lite | GPT-5.3 Codex |
|---|---|---|
| FrontierMath (Tiers 1-3) | 27.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| LMArena Math | 1428 | — |
Knowledge Not comparable
Gemini 3.1 Flash Lite: 41.9 (#104), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Flash Lite | GPT-5.3 Codex |
|---|---|---|
| GPQA Diamond | 81.8% | — |
| Humanity's Last Exam | 8.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| LMArena Expert | 1398 | — |
Multimodal Not comparable
Gemini 3.1 Flash Lite: 39.4 (#60), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Flash Lite | GPT-5.3 Codex |
|---|---|---|
| LMArena Vision | 1240 | — |
Multilingual Not comparable
Gemini 3.1 Flash Lite: 52.3 (#86), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Flash Lite | GPT-5.3 Codex |
|---|---|---|
| LMArena Non-English | 1411 | — |
| LMArena Chinese | 1461 | — |
| LMArena French | 1424 | — |
| LMArena German | 1429 | — |
| LMArena Japanese | 1413 | — |
| LMArena Korean | 1392 | — |
| LMArena Russian | 1420 | — |
| LMArena Spanish | 1421 | — |
Instruction Following Not comparable
Gemini 3.1 Flash Lite: 72.7 (#131), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Flash Lite | GPT-5.3 Codex |
|---|---|---|
| LMArena Instruction Following | 1377 | — |
Long Context Not comparable
Gemini 3.1 Flash Lite: 42.5 (#122), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Flash Lite | GPT-5.3 Codex |
|---|---|---|
| LMArena Longer Query | 1394 | — |
Writing & Preference Not comparable
Gemini 3.1 Flash Lite: 60.9 (#94), GPT-5.3 Codex: —
| Benchmark | Gemini 3.1 Flash Lite | GPT-5.3 Codex |
|---|---|---|
| LMArena Text | 1416 | — |
| LMArena Creative Writing | 1401 | — |
| LMArena Multi-Turn | 1417 | — |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than GPT-5.3 Codex?
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 8.6× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.1 Flash Lite or GPT-5.3 Codex?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.
Is Gemini 3.1 Flash Lite or GPT-5.3 Codex better for coding?
GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 37.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Flash Lite does, with 1.05M tokens against 400K.
How many benchmarks do Gemini 3.1 Flash Lite and GPT-5.3 Codex share?
4 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and GPT-5.3 Codex has 8.