Claude Sonnet 4.6 vs Gemini 3 Pro: Benchmarks, Pricing & Capabilities Compared
TL;DR — Claude Sonnet 4.6 wins for coding · Gemini 3 Pro wins for long-context.
Claude Sonnet 4.6 Anthropic
- Released
- 2026-02-17
- Context window
- 500K tokens
- Input price
- $3.00 / Mtok
- Output price
- $15.00 / Mtok
Key features
- Agent Teams: orchestrate 2-16 Claude instances
- Near-Opus performance at 1/5th cost
- 80.8% SWE-bench Verified
Gemini 3 Pro Google
- Released
- 2025-11-18
- Context window
- 1M tokens
- Input price
- $2.50 / Mtok
- Output price
- $10.00 / Mtok
Key features
- 1M token context window
- Deep Think reasoning mode
- Solved 5/6 IMO 2025 problems
Benchmark comparison
| Benchmark | Claude Sonnet 4.6 | Gemini 3 Pro |
|---|---|---|
| GPQA Diamond | 78.4% | 78.5% ✓ |
| SWE-bench Verified | 80.8% ✓ | 68.2% |
Pricing comparison
| Metric | Claude Sonnet 4.6 | Gemini 3 Pro |
|---|---|---|
| Input ($/Mtok) | $3.00 | $2.50 |
| Output ($/Mtok) | $15.00 | $10.00 |
| Cached input ($/Mtok) | $0.30 | — |
| Cost per 1M-token roundtrip (1M in + 1M out) | $18.00 | $12.50 |
Context window & modalities
| Attribute | Claude Sonnet 4.6 | Gemini 3 Pro |
|---|---|---|
| Context window | 500K tokens | 1M tokens |
| Input modalities | text, image, PDF | text, image, audio, video, PDF |
| Output modalities | text | text |
| Knowledge cutoff | 2025-10 | 2025-09 |
Verdict by use case
Coding
→ Claude Sonnet 4.6
Basis: SWE-bench
Claude Sonnet 4.6 80.8% vs Gemini 3 Pro 68.2% on SWE-bench.
Reasoning
→ Gemini 3 Pro
Basis: GPQA Diamond
Claude Sonnet 4.6 78.4% vs Gemini 3 Pro 78.5% on GPQA Diamond.
Math
Insufficient data
Basis: MATH / AIME
No shared math benchmark.
Long context
→ Gemini 3 Pro
Basis: Context window
Claude Sonnet 4.6 500K tokens vs Gemini 3 Pro 1M tokens.
Cost
→ Gemini 3 Pro
Basis: Input $/Mtok
Claude Sonnet 4.6 $3/Mtok vs Gemini 3 Pro $2.5/Mtok input.
Changelog & releases
Claude Sonnet 4.6
Released 2026-02-17
Predecessor: anthropic-claude-sonnet-4
- Agent Teams: orchestrate 2–16 Claude instances in parallel
- +8.5pt on SWE-bench Verified vs Sonnet 4
- 1/5 the cost of Opus 4.5 at ~95% of coding quality
- Fast mode research preview for lower-latency inference