Model comparison
Claude 3.5 Sonnet vs Gemini 2.0 Flash-Lite
Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.3 to 34.4 on the Noometry Index.
Last verified . 32 shared benchmarks.
GoogleSummary
- They share 32 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 3 categories and Gemini 2.0 Flash-Lite in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.0 Flash-Lite leads 31.8 to 18.0.
- The biggest single-benchmark swing is LiveBench Coding: 67.1% for Claude 3.5 Sonnet and 47.1% for Gemini 2.0 Flash-Lite.
Side by side
| Claude 3.5 Sonnet | Gemini 2.0 Flash-Lite | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 34.4 | 37.3 |
| Released | 2024-06-20 | 2025-02-05 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.5 (#145), Gemini 2.0 Flash-Lite: 37.4 (#181)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.0 Flash-Lite |
|---|---|---|
| LiveBench Coding | 67.1% | 47.1% |
| LMArena Coding | 1343 | 1322 |
| Aider Polyglot | 51.6% | — |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.1 (#61), Gemini 2.0 Flash-Lite: —
| Benchmark | Claude 3.5 Sonnet | Gemini 2.0 Flash-Lite |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 22.5 (#176), Gemini 2.0 Flash-Lite: 21.2 (#203)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.0 Flash-Lite |
|---|---|---|
| LiveBench Reasoning | 56.7% | 50.1% |
| LMArena Hard Prompts | 1305 | 1324 |
| DTBench | 67.8% | 52.5% |
| LiveBench Data Analysis | 55% | 65.5% |
| ForecastBench | 60.7 | 57.1 |
| LiveBench | 59% | 54.3% |
| SimpleBench | 41.4% | — |
| EnigmaEval | 0.9% | — |
| Epoch Capabilities Index | 133.55 | — |
Math Gemini 2.0 Flash-Lite leads
Claude 3.5 Sonnet: 18.0 (#282), Gemini 2.0 Flash-Lite: 31.8 (#192)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.0 Flash-Lite |
|---|---|---|
| Omni-MATH | 27.6% | 37.4% |
| LiveBench Math | 52.3% | 58.1% |
| LMArena Math | 1306 | 1309 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Gemini 2.0 Flash-Lite leads
Claude 3.5 Sonnet: 28.5 (#236), Gemini 2.0 Flash-Lite: 34.6 (#185)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.0 Flash-Lite |
|---|---|---|
| MMLU-Pro | 77.7% | 72% |
| GPQA (HELM) | 56.5% | 50% |
| LMArena Expert | 1264 | 1305 |
| GPQA Diamond | 55.3% | — |
| Humanity's Last Exam | 4.1% | — |
| Confabulations | 19.9% | — |
| MMLU | 87.3% | — |
Multimodal Gemini 2.0 Flash-Lite leads
Claude 3.5 Sonnet: 26.0 (#115), Gemini 2.0 Flash-Lite: 30.6 (#103)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Vision | 1125 | 1100 |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Gemini 2.0 Flash-Lite leads
Claude 3.5 Sonnet: 43.4 (#180), Gemini 2.0 Flash-Lite: 46.2 (#156)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Non-English | 1283 | 1323 |
| LMArena Chinese | 1271 | 1339 |
| LMArena French | 1304 | 1346 |
| LMArena German | 1297 | 1306 |
| LMArena Japanese | 1234 | 1302 |
| LMArena Korean | 1200 | 1325 |
| LMArena Russian | 1305 | 1328 |
| LMArena Spanish | 1289 | 1313 |
Instruction Following Gemini 2.0 Flash-Lite leads
Claude 3.5 Sonnet: 69.0 (#177), Gemini 2.0 Flash-Lite: 70.6 (#158)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.0 Flash-Lite |
|---|---|---|
| LiveBench Instruction Following | 69.3% | 78.3% |
| IFEval | 85.5% | 82.4% |
| LMArena Instruction Following | 1297 | 1305 |
Long Context Too close to call
Claude 3.5 Sonnet: 39.9 (#162), Gemini 2.0 Flash-Lite: 40.1 (#155)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Longer Query | 1311 | 1321 |
Writing & Preference Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 53.0 (#159), Gemini 2.0 Flash-Lite: 51.9 (#172)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Text | 1298 | 1330 |
| LMArena Creative Writing | 1292 | 1319 |
| WildBench | 79.2% | 79% |
| LMArena Multi-Turn | 1326 | 1307 |
| LiveBench Language | 53.8% | 34.3% |
| Short-Story Creative Writing | 80.3% | — |
| EQ-Bench Creative Writing | 1451 | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Gemini 2.0 Flash-Lite?
Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.3 to 34.4 on the Noometry Index.
Is Claude 3.5 Sonnet or Gemini 2.0 Flash-Lite better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.5 versus 37.4 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Gemini 2.0 Flash-Lite share?
32 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Gemini 2.0 Flash-Lite has 32.