Model comparison
Claude Sonnet 4 vs Gemini 3.1 Flash Lite
Claude Sonnet 4 and Gemini 3.1 Flash Lite score almost the same on the Noometry Index (40.8 vs 40.8), so choose on price, context window or the category you care about most.
Last verified . 33 shared benchmarks.
GoogleSummary
- They share 33 benchmarks with published results for both. Claude Sonnet 4 scores higher in 3 categories and Gemini 3.1 Flash Lite in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Gemini 3.1 Flash Lite leads 39.4 to 26.2.
- The biggest single-benchmark swing is DeepResearch Bench: 46.6% for Claude Sonnet 4 and 37.3% for Gemini 3.1 Flash Lite.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Sonnet 4 | Gemini 3.1 Flash Lite | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 40.8 | 40.8 |
| Released | 2025-05-22 | 2026-03-03 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 66K |
| Input $ / M tokens | $3 | $0.25 |
| Output $ / M tokens | $15 | $1.50 |
| Results tracked | 58 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), Gemini 3.1 Flash Lite: 37.8 (#188)
| Benchmark | Claude Sonnet 4 | Gemini 3.1 Flash Lite |
|---|---|---|
| SciCode | 40% | 41.9% |
| WeirdML | 46.1% | 52.2% |
| LMArena Coding | 1414 | 1400 |
| ALE-Bench | 655.35 | 797.73 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1256 |
| GSO | 4.9% | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), Gemini 3.1 Flash Lite: 30.2 (#79)
| Benchmark | Claude Sonnet 4 | Gemini 3.1 Flash Lite |
|---|---|---|
| DeepResearch Bench | 46.6% | 37.3% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Too close to call
Claude Sonnet 4: 22.9 (#187), Gemini 3.1 Flash Lite: 22.9 (#186)
| Benchmark | Claude Sonnet 4 | Gemini 3.1 Flash Lite |
|---|---|---|
| Kagi LLM Benchmark | 73% | 67.2% |
| CritPt | 0.3% | 1.1% |
| EnigmaEval | 3.1% | 3% |
| LMArena Hard Prompts | 1372 | 1407 |
| DTBench | 77.1% | 76.8% |
| LMCA | 29% | 35% |
| Epoch Capabilities Index | 141.69 | 144.47 |
| ForecastBench | 60.2 | 54.4 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| NYT Connections (extended) | — | 8.2% |
| ARC-AGI-1 | 40% | — |
| Chess Puzzles | — | 25% |
| Thematic Generalization | — | 63.3% |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), Gemini 3.1 Flash Lite: 40.7 (#90)
| Benchmark | Claude Sonnet 4 | Gemini 3.1 Flash Lite |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 80% |
| LMArena Math | 1375 | 1428 |
| FrontierMath (Tiers 1-3) | — | 27.7% |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Too close to call
Claude Sonnet 4: 41.8 (#108), Gemini 3.1 Flash Lite: 41.9 (#104)
| Benchmark | Claude Sonnet 4 | Gemini 3.1 Flash Lite |
|---|---|---|
| GPQA Diamond | 79.2% | 81.8% |
| Humanity's Last Exam | 7.8% | 8.6% |
| Vectara Hallucination Rate | 10.3% | 8.2% |
| LMArena Expert | 1372 | 1398 |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Gemini 3.1 Flash Lite leads
Claude Sonnet 4: 26.2 (#121), Gemini 3.1 Flash Lite: 39.4 (#60)
| Benchmark | Claude Sonnet 4 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Vision | 1191 | 1240 |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Gemini 3.1 Flash Lite leads
Claude Sonnet 4: 46.7 (#156), Gemini 3.1 Flash Lite: 52.3 (#86)
| Benchmark | Claude Sonnet 4 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Non-English | 1333 | 1411 |
| LMArena Chinese | 1350 | 1461 |
| LMArena French | 1363 | 1424 |
| LMArena German | 1331 | 1429 |
| LMArena Japanese | 1302 | 1413 |
| LMArena Korean | 1291 | 1392 |
| LMArena Russian | 1355 | 1420 |
| LMArena Spanish | 1357 | 1421 |
Instruction Following Gemini 3.1 Flash Lite leads
Claude Sonnet 4: 71.7 (#145), Gemini 3.1 Flash Lite: 72.7 (#131)
| Benchmark | Claude Sonnet 4 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Instruction Following | 1376 | 1377 |
| IFEval | 84% | — |
Long Context Gemini 3.1 Flash Lite leads
Claude Sonnet 4: 33.7 (#259), Gemini 3.1 Flash Lite: 42.5 (#122)
| Benchmark | Claude Sonnet 4 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Longer Query | 1398 | 1394 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Gemini 3.1 Flash Lite leads
Claude Sonnet 4: 57.1 (#132), Gemini 3.1 Flash Lite: 60.9 (#94)
| Benchmark | Claude Sonnet 4 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Text | 1351 | 1416 |
| LMArena Creative Writing | 1345 | 1401 |
| LMArena Multi-Turn | 1376 | 1417 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Gemini 3.1 Flash Lite?
Claude Sonnet 4 and Gemini 3.1 Flash Lite score almost the same on the Noometry Index (40.8 vs 40.8), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Sonnet 4 or Gemini 3.1 Flash Lite?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Gemini 3.1 Flash Lite better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 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 200K.
How many benchmarks do Claude Sonnet 4 and Gemini 3.1 Flash Lite share?
33 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Gemini 3.1 Flash Lite has 38.