Model comparison
Claude Sonnet 4.6 vs Gemini 3 Pro
Head-to-head evidence from 18 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Sonnet 4.6 #32 (Supported); Gemini 3 Pro #19 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Sonnet 4.6 and Gemini 3 Pro share 18 comparable benchmark results. 2 of 8 categories are comparable. 15 results are unique to Claude Sonnet 4.6; 9 to Gemini 3 Pro.
Updated July 20, 2026- Shared results
- 18
- Claude Sonnet 4.6 only
- 15
- Gemini 3 Pro only
- 9
- Comparable categories
- 2 / 8
Pick Gemini 3 Pro if you want the stronger benchmark profile. Claude Sonnet 4.6 only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
Confidence note. This is a partial-evidence comparison with 18 shared benchmark results across 7 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Gemini 3 Pro has the cleaner BenchAlign overall profile here, landing at 67.73 versus 65.07. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Gemini 3 Pro's sharpest advantage is in mathematics, where it averages 32.9 against 26.4. The single biggest benchmark swing on the page is FrontierMath v2 (Tier 4), 8.300% to 18.750%.
Claude Sonnet 4.6 is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $2.00 input / $12.00 output per 1M tokens for Gemini 3 Pro. Gemini 3 Pro gives you the larger context window at 2M, compared with 200K for Claude Sonnet 4.6.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Claude Sonnet 4.6 | Δ | Gemini 3 Pro |
|---|---|---|---|
| Math | Claude Sonnet 4.626.4 | Margin→ 6.5 | Gemini 3 Pro32.9 |
| Multimodal | Claude Sonnet 4.677.4 | Margin→ 3.7 | Gemini 3 Pro81.1 |
| Agentic | Claude Sonnet 4.665.2 | MarginNo overlap | Gemini 3 ProNot measured |
| Coding | Claude Sonnet 4.669.1 | MarginNo overlap | Gemini 3 ProNot measured |
| Reasoning | Claude Sonnet 4.6Not measured | MarginNo overlap | Gemini 3 Pro31.1 |
| Knowledge | Claude Sonnet 4.666.0 | MarginNo overlap | Gemini 3 ProNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
FrontierMath v2 (Tier 4)
MathA 8.300%B 18.750%Winner: Gemini 3 ProΔ 10.5FrontierMath v2 (Tier 4): Claude Sonnet 4.6 scored 8.300%; Gemini 3 Pro scored 18.750%. Gemini 3 Pro wins this benchmark. - Source ↗
FrontierMath v2 (Tiers 1-3)
MathA 32.400%B 37.600%Winner: Gemini 3 ProΔ 5.2FrontierMath v2 (Tiers 1-3): Claude Sonnet 4.6 scored 32.400%; Gemini 3 Pro scored 37.600%. Gemini 3 Pro wins this benchmark. - Source ↗
CharXiv
MultimodalA 77.4%B 81.4%Winner: Gemini 3 ProΔ 4CharXiv: Claude Sonnet 4.6 scored 77.4%; Gemini 3 Pro scored 81.4%. Gemini 3 Pro wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude Sonnet 4.6 | Gemini 3 Pro | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Sonnet 4.6$3 input / $15 output | Gemini 3 Pro$2 input / $12 output | Gemini 3 Pro has the lower combined listed price. |
| Generation speedtokens per second | Claude Sonnet 4.644 tok/s | Gemini 3 Pro109 tok/s | Gemini 3 Pro has the higher measured throughput. |
| First-answer latencyseconds to first token | Claude Sonnet 4.61.48 s | Gemini 3 Pro32.65 s | Claude Sonnet 4.6 reaches the first token sooner. |
| Context windowmaximum listed tokens | Claude Sonnet 4.6200K | Gemini 3 Pro2M | Gemini 3 Pro lists the larger context window. |
Benchmark Deep Dive
Agentic8 benchmarks
| Benchmark | Claude Sonnet 4.6 | Gemini 3 Pro | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 59.1% | — | Not comparable |
| OSWorld-VerifiedSource | 72.1% | — | Not comparable |
| Claw-EvalSource | 67.8% | — | Not comparable |
| CyberGymSource | 65.2% | — | Not comparable |
| τ²-bench resultsSource | 79.5% | 87.1% | Gemini 3 Pro leads |
| Gert LabsSource | 62.92% | 63.23% | Gemini 3 Pro leads |
| OSWorld 2.0Source | 8.3% | — | Not comparable |
| JobBenchSource | 36.9% | 11.4% | Claude Sonnet 4.6 leads |
Coding8 benchmarks
| Benchmark | Claude Sonnet 4.6 | Gemini 3 Pro | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 79.6% | — | Not comparable |
| SWE-RebenchSource | 60.7% | — | Not comparable |
| React Native EvalsSource | 80.6% | — | Not comparable |
| Vibe Code BenchSource | 51.48% | 14.30% | Claude Sonnet 4.6 leads |
| cursorBench31Source | 48.8% | — | Not comparable |
| AA-SciCodeSource | 46.9% | 56.1% | Gemini 3 Pro leads |
| FrontierCode 1.1 MainSource | 24.3% | — | Not comparable |
| AA LiveCodeBenchSource | — | 91.7% | Not comparable |
Reasoning3 benchmarks
Knowledge11 benchmarks
| Benchmark | Claude Sonnet 4.6 | Gemini 3 Pro | Result |
|---|---|---|---|
| GPQASource | 89.9% | — | Not comparable |
| SuperGPQASource | 95% | — | Not comparable |
| MMLU-ProSource | 79.2% | — | Not comparable |
| HLESource | 49% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 35.9% | 39.5% | Gemini 3 Pro leads |
| AA-GPQA DiamondSource | 79.9% | 90.8% | Gemini 3 Pro leads |
| AA-HLESource | 13.2% | 37.2% | Gemini 3 Pro leads |
| AA-Omniscience IndexSource | -2.9% | 15.8% | Gemini 3 Pro leads |
| AA-Omniscience AccuracySource | 38.0% | 55.9% | Gemini 3 Pro leads |
| AA-Omniscience Hallucination RateSource | 65.9% | 90.9% | Claude Sonnet 4.6 leads |
| AA MMLU-ProSource | — | 89.8% | Not comparable |
MathGemini 3 Pro wins2 benchmarks
Multilingual1 benchmarks
| Benchmark | Claude Sonnet 4.6 | Gemini 3 Pro | Result |
|---|---|---|---|
| AA Global-MMLU-LiteSource | — | 92.2% | Not comparable |
MultimodalGemini 3 Pro wins8 benchmarks
| Benchmark | Claude Sonnet 4.6 | Gemini 3 Pro | Result |
|---|---|---|---|
| CharXivSource | 77.4% | 81.4% | Gemini 3 Pro leads |
| AA-MMMU-ProSource | 70.6% | 80.2% | Gemini 3 Pro leads |
| Design Arena WebsiteSource | 1317 | — | Not comparable |
| MMMU-ProSource | — | 81% | Not comparable |
| MathVisionSource | — | 86.6% | Not comparable |
| VideoMMMUSource | — | 87.6% | Not comparable |
| ScreenSpot ProSource | — | 72.7% | Not comparable |
| V*Source | — | 88.0% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Claude Sonnet 4.6 | Gemini 3 Pro | Result |
|---|---|---|---|
| AA-IFBenchSource | 41.2% | 70.4% | Gemini 3 Pro leads |
Frequently Asked Questions (3)
Which is better, Claude Sonnet 4.6 or Gemini 3 Pro?
Gemini 3 Pro is ahead on BenchLM's BenchAlign leaderboard, 67.73 to 65.07. The biggest single separator in this matchup is FrontierMath v2 (Tier 4), where the scores are 8.300% and 18.750%.
Which is better for math, Claude Sonnet 4.6 or Gemini 3 Pro?
Gemini 3 Pro has the edge for math in this comparison, averaging 32.9 versus 26.4. Inside this category, FrontierMath v2 (Tier 4) is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, Claude Sonnet 4.6 or Gemini 3 Pro?
Gemini 3 Pro has the edge for multimodal and grounded tasks in this comparison, averaging 81.1 versus 77.4. Inside this category, AA-MMMU-Pro is the benchmark that creates the most daylight between them.
Related Comparisons
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.