Claude Haiku 3.5
| Released | 2024-10-22 |
|---|---|
| Price per 1M | $0.80 in · $4.00 out |
| Overall score | 35.5 · rank 215 |
| Context window | 200,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 35.5 | 215 | 14 |
| Overall: Coding | 36.0 | 202 | 6 |
| Overall: Reasoning | 33.3 | 226 | 6 |
| Overall: Agentic work | 37.2 | 203 | 6 |
| Overall: Frontend | 35.7 | 199 | 5 |
| Coding | 35.0 | 189 | 3 |
| Agents | 38.5 | 162 | 1 |
| Reasoning | 36.1 | 219 | 2 |
| Math | 34.1 | 185 | 3 |
| Knowledge | 25.6 | 167 | 1 |
| General | 40.1 | 163 | 2 |
| Multimodal | 37.5 | 114 | 2 |
| Value vs price | −13.7 | 185 |
Evidence
Coding 35.0 ±2.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SciCode | 27.4% | Epoch AI | 2026-11-11 |
| Aider Polyglot | 28.0% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 41.9% | Vals AI | 2026-09-01 |
Agents 38.5 ±7.1
Reasoning 36.1 ±4.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CritPt | 0.0% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 38.1% | Epoch AI | 2025-03-12 |
| GPQA Diamond (Vals run) | 37.9% | Vals AI | 2026-09-01 |
Math 34.1 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 (2025 set) | 0.3% | Epoch AI | 2025-03-07 |
| MATH Level 5 | 46.4% | Epoch AI | 2025-03-12 |
| OTIS Mock AIME 2024-2025 | 4.3% | Epoch AI | 2025-02-25 |
Knowledge 25.6 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 64.1% | Vals AI | 2026-09-01 |
General 40.1 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench Creative Writing v3 | 1,144 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,325 | LMArena | 2026-11-09 |
Multimodal 37.5 ±4.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,127 | LMArena | 2026-11-09 |
| GeoBench | 34.0% | Epoch AI | 2026-11-11 |
Names matched to this model
claude-haiku-3-5, claude-haiku-3-5-20241022