Claude Sonnet 4.5vsClaude Sonnet 4
Across 26 shared benchmarks, Claude Sonnet 4.5 leads overall: Claude Sonnet 4.5 wins 22, Claude Sonnet 4 wins 2, with 2 ties and an average score difference of +19.53.
Claude Sonnet 4.5
Anthropic · 2025-09-30 · Chat model
Claude Sonnet 4
Anthropic · 2025-05-23 · Reasoning model
Claude Sonnet 4.522 wins(85%)Ties2(8%)2 winsClaude Sonnet 4
Benchmark scores
Grouped by capability, sorted by largest gap within each. 26 shared benchmarks.
Agent Level Benchmark
Claude Sonnet 4.5 4/4| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 4 | Diff |
|---|---|---|---|
| τ²-Bench | 7126 / 44Normal (With Tools) | 5235 / 44Normal (With Tools) | +19 |
| τ²-Bench - Telecom | 70.50138 / 264Normal (With Tools) | 52.30169 / 264Normal (With Tools) | +18.20 |
| τ³-Banking | 24.5080 / 164Thinking (With Tools) | 16.70100 / 164Thinking (With Tools) | +7.80 |
| Terminal Bench Hard | 28.80116 / 244Normal (With Tools) | 27.30120 / 244Normal (With Tools) | +1.50 |
Coding and Software Engineer
Claude Sonnet 4.5 4/4| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 4 | Diff |
|---|---|---|---|
| CodeClash | 1,3891 / 8Normal (With Tools) | 1,2234 / 8Normal (With Tools) | +166 |
| LiveCodeBench | 59136 / 250Normal (No Tools) | 48.50170 / 250Normal (No Tools) | +10.50 |
| SWE-bench Verified | 828 / 116Parallel Thinking (With Tools) | 80.2014 / 116Parallel Thinking (With Tools) | +1.80 |
| SWE-Bench Pro - Public | 43.6054 / 62Thinking (No Tools) | 42.7055 / 62Thinking (No Tools) | +0.90 |
Math and Reasoning
Even 4/4| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 4 | Diff |
|---|---|---|---|
| FrontierMath | 5.2038 / 60Normal (No Tools) | 4.1041 / 60Normal (No Tools) | +1.10 |
| AIME2025 | 37173 / 215Normal (No Tools) | 38170 / 215Normal (No Tools) | -1 |
| IMO-ProofBench | 27.108 / 16Thinking (No Tools) | 27.108 / 16Thinking (No Tools) | — |
| IMO-ProofBench Advanced | 4.8019 / 24Thinking (No Tools) | 4.8019 / 24Thinking (No Tools) | — |
AI Agent - Tool Usage
Claude Sonnet 4.5 3/3| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 4 | Diff |
|---|---|---|---|
| Terminal-Bench 2.1 | 55.80120 / 192Thinking (With Tools) | 36.30150 / 192Thinking (With Tools) | +19.50 |
| OSWorld-Verified | 61.4022 / 26Thinking (With Tools) | 42.2024 / 26Thinking (With Tools) | +19.20 |
| Terminal-Bench | 2725 / 35Normal (With Tools) | 2626 / 35Normal (With Tools) | +1 |
General Knowledge
Claude Sonnet 4.5 3/3| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 4 | Diff |
|---|---|---|---|
| MMLU Pro | 888 / 176Thinking (No Tools) | 8440 / 176Thinking (No Tools) | +4 |
| LiveBench | 53.6985 / 117Normal (No Tools) | 50.9891 / 117Normal (No Tools) | +2.71 |
| ARC-AGI-1 | 25.50127 / 147Normal (No Tools) | 23.80128 / 147Normal (No Tools) | +1.70 |
Claw-style Agent Evaluation
Claude Sonnet 4.5 2/2| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 4 | Diff |
|---|---|---|---|
| Claw Bench | 88.1013 / 29Thinking (With Tools) | 77.8023 / 29Thinking (With Tools) | +10.30 |
| Pinch Bench | 88.205 / 38Thinking (With Tools) | 80.5023 / 38Thinking (With Tools) | +7.70 |
General Evaluation
Claude Sonnet 4.5 1/1| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 4 | Diff |
|---|---|---|---|
| GPQA Diamond | 73.70292 / 462Normal (No Tools) | 68337 / 462Normal (No Tools) | +5.70 |
Instruction Following
Claude Sonnet 4 1/1| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 4 | Diff |
|---|---|---|---|
| IF Bench | 42.70199 / 282Normal (No Tools) | 45.40180 / 282Normal (No Tools) | -2.70 |
Long Context
Claude Sonnet 4.5 1/1| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 4 | Diff |
|---|---|---|---|
| AA-LCR | 54133 / 170Normal (No Tools) | 44150 / 170Normal (No Tools) | +10 |
Multimodal Understanding
Claude Sonnet 4.5 1/1| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 4 | Diff |
|---|---|---|---|
| MMMU-Pro | 65.20151 / 227Normal (No Tools) | 62.40163 / 227Normal (No Tools) | +2.80 |
Productivity Knowledge
Claude Sonnet 4.5 1/1| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 4 | Diff |
|---|---|---|---|
| GDPval-AA | 3910 / 15Thinking (No Tools) | 3313 / 15Thinking (No Tools) | +6 |
Writing and Creative Capabilities
Claude Sonnet 4.5 1/1| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 4 | Diff |
|---|---|---|---|
| Creative Writing | 1,67430 / 106Normal (No Tools) | 1,48053 / 106Normal (No Tools) | +194.10 |
Specs
| Field | Claude Sonnet 4.5 | Claude Sonnet 4 |
|---|---|---|
| Publisher | Anthropic | Anthropic |
| Release date | 2025-09-30 | 2025-05-23 |
| Model type | Chat model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1000K | 200K |
| Max output | 64K | 64K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Claude Sonnet 4.5 | Claude Sonnet 4 |
|---|---|---|
| Text input | $3 / 1M tokens | $3 / 1M tokens |
| Text output | $15 / 1M tokens | $15 / 1M tokens |
| Cache read | $0.3 / 1M tokens | $0.3 / 1M tokens |
| Cache write | $3.75 / 1M tokens | $3.75 / 1M tokens |
Summary
- Claude Sonnet 4.5leads in:Agent Level Benchmark (4/4), Coding and Software Engineer (4/4), AI Agent - Tool Usage (3/3), General Knowledge (3/3), Claw-style Agent Evaluation (2/2), General Evaluation (1/1), Long Context (1/1), Multimodal Understanding (1/1), Productivity Knowledge (1/1), Writing and Creative Capabilities (1/1)
- Claude Sonnet 4leads in:Instruction Following (1/1)
- Tied in:Math and Reasoning
On average across the 26 shared benchmarks, Claude Sonnet 4.5 scores 19.53 higher.
Largest single-benchmark gap: Creative Writing — Claude Sonnet 4.5 1,674 vs Claude Sonnet 4 1,480 (+194.10).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.