Claude Sonnet 4.6vsGPT-5.2
Across 9 shared benchmarks, Claude Sonnet 4.6 leads overall: Claude Sonnet 4.6 wins 8, GPT-5.2 wins 1, with 0 ties and an average score difference of +20.83.
Claude Sonnet 4.6
Anthropic · 2026-02-17 · Chat model
GPT-5.2
OpenAI · 2025-12-11 · Chat model
Claude Sonnet 4.68 wins(89%)(11%)1 winGPT-5.2
Benchmark scores
Grouped by capability, sorted by largest gap within each. 9 shared benchmarks.
Agent Level Benchmark
Claude Sonnet 4.6 2/2| Benchmark | Claude Sonnet 4.6 | GPT-5.2 | Diff |
|---|---|---|---|
| τ²-Bench - Telecom | 79.50115 / 264Normal (With Tools) | 46.50178 / 264Normal (With Tools) | +33 |
| Terminal Bench Hard | 46.2029 / 244Normal (With Tools) | 31.80100 / 244Normal (With Tools) | +14.40 |
General Knowledge
Claude Sonnet 4.6 2/2| Benchmark | Claude Sonnet 4.6 | GPT-5.2 | Diff |
|---|---|---|---|
| HLE | 13.30355 / 563Normal (No Tools) · Text only | 8419 / 563Normal (No Tools) · Text only | +5.30 |
| CritPt | 0.90158 / 200Normal (No Tools) | 0.60168 / 200Normal (No Tools) | +0.30 |
General Evaluation
Claude Sonnet 4.6 1/1| Benchmark | Claude Sonnet 4.6 | GPT-5.2 | Diff |
|---|---|---|---|
| GPQA Diamond | 79.90237 / 462Normal (No Tools) | 73.23298 / 462Normal (No Tools) | +6.67 |
Instruction Following
GPT-5.2 1/1| Benchmark | Claude Sonnet 4.6 | GPT-5.2 | Diff |
|---|---|---|---|
| IF Bench | 42.40201 / 282Normal (No Tools) | 47.40168 / 282Normal (No Tools) | -5 |
Long Context
Claude Sonnet 4.6 1/1| Benchmark | Claude Sonnet 4.6 | GPT-5.2 | Diff |
|---|---|---|---|
| AA-LCR | 69.30107 / 170Normal (No Tools) | 45.70144 / 170Normal (No Tools) | +23.60 |
Multimodal Understanding
Claude Sonnet 4.6 1/1| Benchmark | Claude Sonnet 4.6 | GPT-5.2 | Diff |
|---|---|---|---|
| MMMU-Pro | 70.60123 / 227Normal (No Tools) | 65.80148 / 227Normal (No Tools) | +4.80 |
Writing and Creative Capabilities
Claude Sonnet 4.6 1/1| Benchmark | Claude Sonnet 4.6 | GPT-5.2 | Diff |
|---|---|---|---|
| Creative Writing | 1,80418 / 106Normal (No Tools) | 1,70026 / 106Normal (No Tools) | +104.40 |
Specs
| Field | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| Publisher | Anthropic | OpenAI |
| Release date | 2026-02-17 | 2025-12-11 |
| Model type | Chat model | Chat model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1M | 400K |
| Max output | 8K | Not available |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| Text input | $3 / 1M tokens | $1.75 / 1M tokens |
| Text output | $15 / 1M tokens | $14 / 1M tokens |
| Cache read | $0.3 / 1M tokens | $0.175 / 1M tokens |
| Cache write | $3.75 / 1M tokens | $1.75 / 1M tokens |
Summary
- Claude Sonnet 4.6leads in:Agent Level Benchmark (2/2), General Knowledge (2/2), General Evaluation (1/1), Long Context (1/1), Multimodal Understanding (1/1), Writing and Creative Capabilities (1/1)
- GPT-5.2leads in:Instruction Following (1/1)
On average across the 9 shared benchmarks, Claude Sonnet 4.6 scores 20.83 higher.
Largest single-benchmark gap: Creative Writing — Claude Sonnet 4.6 1,804 vs GPT-5.2 1,700 (+104.40).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.