Claude Haiku 4.5 (latest)
| Released | 2025-10-15 |
|---|---|
| Price per 1M | $1.00 in · $5.00 out |
| Overall score | 50.6 (early, few results) |
| Context window | 200,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 50.6 | 4 | |
| Overall: Coding | 48.3 | 3 | |
| Overall: Reasoning | 48.3 | 3 | |
| Overall: Agentic work | 48.3 | 3 | |
| Reasoning | 48.3 | 3 | |
| General | 54.0 | 1 | |
| Value vs price | +0.8 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 48.5 ±5.4 | 4 |
| Thinking | 49.6 ±5.7 | 2 |
Evidence
Reasoning 48.3 ±3.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 (ARC Prize verified) | 4.0% | ARC Prize | 2026-11-11 |
| Extended NYT Connections | 14.3% | Lech Mazur | 2026-11-10 |
| ARC-AGI-1 (ARC Prize verified) | 47.7% | ARC Prize | 2026-11-11 |
General 54.0 ±5.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench Longform Creative Writing | 65.0% | EQ-Bench | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 (ARC Prize verified) | 14.3% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 1.3% | ARC Prize | A stronger configuration result was used |
Names matched to this model
claude-haiku-4-5, claude-haiku-4-5-latest