Claude Sonnet 4.6 vs GPT-5.2: Benchmarks, Pricing & Capabilities Compared
TL;DR — Claude Sonnet 4.6 wins for coding + long-context · GPT-5.2 wins for cost.
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
GPT-5.2 OpenAI
- Released
- 2025-12-11
- Context window
- 400K tokens
- Input price
- $2.00 / Mtok
- Output price
- $10.00 / Mtok
Key features
- Enhanced reasoning capabilities
- Improved adaptive reasoning
- Better multimodal understanding
Benchmark comparison
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| AIME 2025 | 88.5% | 92.1% ✓ |
| GPQA Diamond | 78.4% | 80.1% ✓ |
| SWE-bench Verified | 80.8% ✓ | 72.5% |
Pricing comparison
| Metric | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| Input ($/Mtok) | $3.00 | $2.00 |
| Output ($/Mtok) | $15.00 | $10.00 |
| Cached input ($/Mtok) | $0.30 | — |
| Cost per 1M-token roundtrip (1M in + 1M out) | $18.00 | $12.00 |
Context window & modalities
| Attribute | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| Context window | 500K tokens | 400K tokens |
| Input modalities | text, image, PDF | text, image, audio |
| Output modalities | text | text, audio |
| Knowledge cutoff | 2025-10 | 2025-08 |
Verdict by use case
Coding
→ Claude Sonnet 4.6
Basis: SWE-bench
Claude Sonnet 4.6 80.8% vs GPT-5.2 72.5% on SWE-bench.
Reasoning
→ GPT-5.2
Basis: GPQA Diamond
Claude Sonnet 4.6 78.4% vs GPT-5.2 80.1% on GPQA Diamond.
Math
→ GPT-5.2
Basis: AIME 2025
Claude Sonnet 4.6 88.5% vs GPT-5.2 92.1% on AIME 2025.
Long context
→ Claude Sonnet 4.6
Basis: Context window
Claude Sonnet 4.6 500K tokens vs GPT-5.2 400K tokens.
Cost
→ GPT-5.2
Basis: Input $/Mtok
Claude Sonnet 4.6 $3/Mtok vs GPT-5.2 $2/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