Model comparison
Claude 3 Sonnet vs Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.4 to 28.8 on the Noometry Index.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Gemini 3.1 Flash Lite in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3.1 Flash Lite leads 39.5 to 10.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 80% for Gemini 3.1 Flash Lite.
Side by side
| Claude 3 Sonnet | Gemini 3.1 Flash Lite | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 28.8 | 40.4 |
| Released | 2024-02-29 | 2026-03-03 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $1.50 |
| Results tracked | 30 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Flash Lite leads
Claude 3 Sonnet: 29.2 (#296), Gemini 3.1 Flash Lite: 37.5 (#179)
| Benchmark | Claude 3 Sonnet | Gemini 3.1 Flash Lite |
|---|---|---|
| WeirdML | 10.2% | 52.2% |
| LMArena Coding | 1223 | 1400 |
| LMArena WebDev | — | 1256 |
| SciCode | — | 41.9% |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 797.73 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Agentic & Tool Use Not comparable
Claude 3 Sonnet: —, Gemini 3.1 Flash Lite: 29.9 (#72)
| Benchmark | Claude 3 Sonnet | Gemini 3.1 Flash Lite |
|---|---|---|
| DeepResearch Bench | — | 37.3% |
Reasoning Gemini 3.1 Flash Lite leads
Claude 3 Sonnet: 19.7 (#232), Gemini 3.1 Flash Lite: 22.3 (#181)
| Benchmark | Claude 3 Sonnet | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1407 |
| DTBench | 53.6% | 76.8% |
| Epoch Capabilities Index | 120.69 | 144.45 |
| Kagi LLM Benchmark | — | 67.2% |
| NYT Connections (extended) | — | 8.2% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 25% |
| EnigmaEval | — | 3% |
| Thematic Generalization | — | 63.3% |
| LMCA | — | 35% |
| ForecastBench | — | 54.4 |
| WinoGrande | 75.1% | — |
Math Gemini 3.1 Flash Lite leads
Claude 3 Sonnet: 10.0 (#305), Gemini 3.1 Flash Lite: 39.5 (#82)
| Benchmark | Claude 3 Sonnet | Gemini 3.1 Flash Lite |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 80% |
| LMArena Math | 1213 | 1427 |
| FrontierMath (Tiers 1-3) | — | 27.7% |
| MATH Level 5 | 18.2% | — |
Knowledge Gemini 3.1 Flash Lite leads
Claude 3 Sonnet: 21.1 (#271), Gemini 3.1 Flash Lite: 41.7 (#95)
| Benchmark | Claude 3 Sonnet | Gemini 3.1 Flash Lite |
|---|---|---|
| GPQA Diamond | 40.6% | 81.8% |
| LMArena Expert | 1173 | 1397 |
| Humanity's Last Exam | — | 8.6% |
| Vectara Hallucination Rate | — | 8.2% |
| MMLU | 75.9% | — |
Multimodal Gemini 3.1 Flash Lite leads
Claude 3 Sonnet: 24.7 (#120), Gemini 3.1 Flash Lite: 38.7 (#57)
| Benchmark | Claude 3 Sonnet | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Vision | 984 | 1240 |
Multilingual Gemini 3.1 Flash Lite leads
Claude 3 Sonnet: 38.0 (#229), Gemini 3.1 Flash Lite: 52.5 (#82)
| Benchmark | Claude 3 Sonnet | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Non-English | 1205 | 1410 |
| LMArena Chinese | 1188 | 1461 |
| LMArena French | 1228 | 1423 |
| LMArena German | 1204 | 1429 |
| LMArena Japanese | 1131 | 1411 |
| LMArena Korean | 1128 | 1393 |
| LMArena Russian | 1227 | 1420 |
| LMArena Spanish | 1204 | 1420 |
Instruction Following Gemini 3.1 Flash Lite leads
Claude 3 Sonnet: 63.1 (#230), Gemini 3.1 Flash Lite: 72.9 (#126)
| Benchmark | Claude 3 Sonnet | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Instruction Following | 1200 | 1376 |
Long Context Gemini 3.1 Flash Lite leads
Claude 3 Sonnet: 36.7 (#223), Gemini 3.1 Flash Lite: 42.5 (#117)
| Benchmark | Claude 3 Sonnet | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Longer Query | 1211 | 1394 |
Writing & Preference Gemini 3.1 Flash Lite leads
Claude 3 Sonnet: 42.3 (#233), Gemini 3.1 Flash Lite: 61.0 (#90)
| Benchmark | Claude 3 Sonnet | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Text | 1218 | 1416 |
| LMArena Creative Writing | 1186 | 1401 |
| LMArena Multi-Turn | 1227 | 1417 |
Frequently asked questions
Is Claude 3 Sonnet better than Gemini 3.1 Flash Lite?
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.4 to 28.8 on the Noometry Index.
Is Claude 3 Sonnet or Gemini 3.1 Flash Lite better for coding?
Gemini 3.1 Flash Lite scores higher on coding benchmarks: 37.5 versus 29.2 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Gemini 3.1 Flash Lite share?
23 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Gemini 3.1 Flash Lite has 38.