Model comparison
Claude Sonnet 4 vs Gemini 2.5 Flash-Lite
Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 34× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
GoogleSummary
- They share 32 benchmarks with published results for both. Claude Sonnet 4 scores higher in 8 categories and Gemini 2.5 Flash-Lite in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Sonnet 4 leads 38.3 to 27.8.
- The biggest single-benchmark swing is GPQA (HELM): 70.6% for Claude Sonnet 4 and 30.9% for Gemini 2.5 Flash-Lite.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Sonnet 4 | Gemini 2.5 Flash-Lite | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 40.6 | 36.4 |
| Released | 2025-05-22 | 2025-06-17 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 66K |
| Input $ / M tokens | $3 | $0.10 |
| Output $ / M tokens | $15 | $0.40 |
| Results tracked | 58 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 44.0 (#70), Gemini 2.5 Flash-Lite: 38.0 (#167)
| Benchmark | Claude Sonnet 4 | Gemini 2.5 Flash-Lite |
|---|---|---|
| WeirdML | 46.1% | 35.2% |
| LMArena Coding | 1414 | 1373 |
| ALE-Bench | 655.35 | 325.9 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.3 (#29), Gemini 2.5 Flash-Lite: 27.8 (#89)
| Benchmark | Claude Sonnet 4 | Gemini 2.5 Flash-Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 36.9% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 23.0 (#169), Gemini 2.5 Flash-Lite: 21.5 (#196)
| Benchmark | Claude Sonnet 4 | Gemini 2.5 Flash-Lite |
|---|---|---|
| Kagi LLM Benchmark | 73% | 40.5% |
| LMArena Hard Prompts | 1372 | 1377 |
| DTBench | 77.1% | 62.8% |
| LMCA | 29% | 18.1% |
| Epoch Capabilities Index | 141.69 | 133.93 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| ForecastBench | 60.2 | — |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 41.5 (#71), Gemini 2.5 Flash-Lite: 35.5 (#144)
| Benchmark | Claude Sonnet 4 | Gemini 2.5 Flash-Lite |
|---|---|---|
| Omni-MATH | 60.2% | 48% |
| LMArena Math | 1375 | 1373 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.6 (#99), Gemini 2.5 Flash-Lite: 32.1 (#206)
| Benchmark | Claude Sonnet 4 | Gemini 2.5 Flash-Lite |
|---|---|---|
| MMLU-Pro | 84.3% | 53.7% |
| Vectara Hallucination Rate | 10.3% | 3.3% |
| GPQA (HELM) | 70.6% | 30.9% |
| LMArena Expert | 1371 | 1373 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| Confabulations | 13.2% | — |
Multimodal Gemini 2.5 Flash-Lite leads
Claude Sonnet 4: 25.6 (#116), Gemini 2.5 Flash-Lite: 28.6 (#109)
| Benchmark | Claude Sonnet 4 | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Vision | 1191 | 1198 |
| VPCT | 34% | 30% |
| GeoBench | 37% | — |
| MindCube | 44.8% | — |
Multilingual Gemini 2.5 Flash-Lite leads
Claude Sonnet 4: 46.9 (#151), Gemini 2.5 Flash-Lite: 49.5 (#129)
| Benchmark | Claude Sonnet 4 | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Non-English | 1333 | 1369 |
| LMArena Chinese | 1351 | 1404 |
| LMArena French | 1364 | 1388 |
| LMArena German | 1331 | 1390 |
| LMArena Japanese | 1301 | 1359 |
| LMArena Korean | 1293 | 1358 |
| LMArena Russian | 1355 | 1373 |
| LMArena Spanish | 1356 | 1396 |
Instruction Following Claude Sonnet 4 leads
Claude Sonnet 4: 71.8 (#141), Gemini 2.5 Flash-Lite: 70.2 (#163)
| Benchmark | Claude Sonnet 4 | Gemini 2.5 Flash-Lite |
|---|---|---|
| IFEval | 84% | 81% |
| LMArena Instruction Following | 1375 | 1366 |
Long Context Too close to call
Claude Sonnet 4: 33.6 (#254), Gemini 2.5 Flash-Lite: 33.3 (#257)
| Benchmark | Claude Sonnet 4 | Gemini 2.5 Flash-Lite |
|---|---|---|
| Fiction.LiveBench | 46.9% | 47.2% |
| LMArena Longer Query | 1398 | 1373 |
Writing & Preference Too close to call
Claude Sonnet 4: 57.3 (#127), Gemini 2.5 Flash-Lite: 57.0 (#130)
| Benchmark | Claude Sonnet 4 | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Text | 1351 | 1379 |
| LMArena Creative Writing | 1345 | 1366 |
| WildBench | 83.8% | 81.8% |
| LMArena Multi-Turn | 1376 | 1367 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
Frequently asked questions
Is Claude Sonnet 4 better than Gemini 2.5 Flash-Lite?
Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 34× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4 or Gemini 2.5 Flash-Lite?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Gemini 2.5 Flash-Lite better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 44.0 versus 38.0 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 200K.
How many benchmarks do Claude Sonnet 4 and Gemini 2.5 Flash-Lite share?
32 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Gemini 2.5 Flash-Lite has 33.