Model comparison
Claude Sonnet 4.6 vs Gemini 3.5 Flash Lite
Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 41.8 on the Noometry Index. Gemini 3.5 Flash Lite costs 7.1× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Last verified . 36 shared benchmarks.
GoogleSummary
- They share 36 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 9 categories and Gemini 3.5 Flash Lite in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4.6 leads 51.9 to 25.7.
- The biggest single-benchmark swing is ARC-AGI-2: 60.4% for Claude Sonnet 4.6 and 10.3% for Gemini 3.5 Flash Lite.
- Gemini 3.5 Flash Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- Gemini 3.5 Flash Lite accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Sonnet 4.6 | Gemini 3.5 Flash Lite | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 50.1 | 41.8 |
| Released | 2026-02-17 | 2026-07-21 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 66K |
| Input $ / M tokens | $3 | $0.30 |
| Output $ / M tokens | $15 | $2.50 |
| Results tracked | 57 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.0 (#62), Gemini 3.5 Flash Lite: 42.1 (#96)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena WebDev | 1521 | 1440 |
| SciCode | 46.8% | 41.3% |
| WeirdML | 66.1% | 39% |
| LMArena Coding | 1504 | 1455 |
| ALE-Bench | 1,327 | 765.27 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
Agentic & Tool Use Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 39.1 (#26), Gemini 3.5 Flash Lite: 28.6 (#82)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.5 Flash Lite |
|---|---|---|
| GDP.pdf | 18% | 10% |
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |
Reasoning Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.1 (#40), Gemini 3.5 Flash Lite: 27.8 (#95)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.5 Flash Lite |
|---|---|---|
| ARC-AGI-2 | 60.4% | 10.3% |
| NYT Connections (extended) | 80.9% | 60.4% |
| ARC-AGI-1 | 86.5% | 53.5% |
| CritPt | 3.1% | 0% |
| Chess Puzzles | 13% | 22% |
| LMArena Hard Prompts | 1485 | 1441 |
| Mystery Game Puzzles | 16% | 19% |
| DTBench | 89.9% | 83.5% |
| LMCA | 46.5% | 37.6% |
| Epoch Capabilities Index | 152.25 | 145.12 |
| Thematic Generalization | 76.3% | — |
| ForecastBench | 62 | — |
Math Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 51.9 (#41), Gemini 3.5 Flash Lite: 25.7 (#245)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.5 Flash Lite |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 71.1% |
| ProofBench | 45% | 13% |
| LMArena Math | 1463 | 1431 |
| FrontierMath (Tiers 1-3) | — | 26% |
| FrontierMath Tier 4 | — | 0% |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
Knowledge Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 51.6 (#60), Gemini 3.5 Flash Lite: 50.0 (#66)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.5 Flash Lite |
|---|---|---|
| GPQA Diamond | 87.4% | 83.3% |
| LMArena Expert | 1500 | 1430 |
| SimpleQA Verified | 35.5% | — |
| Vectara Hallucination Rate | 10.6% | — |
Multimodal Gemini 3.5 Flash Lite leads
Claude Sonnet 4.6: 38.0 (#61), Gemini 3.5 Flash Lite: 40.3 (#38)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Vision | 1283 | 1266 |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |
Multilingual Too close to call
Claude Sonnet 4.6: 54.6 (#39), Gemini 3.5 Flash Lite: 53.8 (#59)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Non-English | 1440 | 1428 |
| LMArena Chinese | 1491 | 1467 |
| LMArena French | 1465 | 1452 |
| LMArena German | 1428 | 1454 |
| LMArena Japanese | 1419 | 1428 |
| LMArena Korean | 1411 | 1406 |
| LMArena Russian | 1440 | 1443 |
| LMArena Spanish | 1465 | 1440 |
Instruction Following Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 77.6 (#23), Gemini 3.5 Flash Lite: 75.0 (#77)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Instruction Following | 1476 | 1420 |
Long Context Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 45.3 (#40), Gemini 3.5 Flash Lite: 43.8 (#80)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Longer Query | 1479 | 1435 |
Writing & Preference Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 70.4 (#22), Gemini 3.5 Flash Lite: 64.4 (#55)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Text | 1458 | 1436 |
| LMArena Creative Writing | 1435 | 1419 |
| EQ-Bench Creative Writing | 1810 | 1559 |
| LMArena Multi-Turn | 1464 | 1445 |
| EQ-Bench 4 | 1207 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than Gemini 3.5 Flash Lite?
Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 41.8 on the Noometry Index. Gemini 3.5 Flash Lite costs 7.1× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4.6 or Gemini 3.5 Flash Lite?
Gemini 3.5 Flash Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or Gemini 3.5 Flash Lite better for coding?
Claude Sonnet 4.6 scores higher on coding benchmarks: 46.0 versus 42.1 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.5 Flash Lite does, with 1.05M tokens against 1M.
How many benchmarks do Claude Sonnet 4.6 and Gemini 3.5 Flash Lite share?
36 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Gemini 3.5 Flash Lite has 38.