Updated daily at 05:00 UTC
- Released
- 13 Mar 2024
- Status
- Retired
- Retired
- 20 Apr 2026
- Context
- 200K
- Max output
- 4.1K
- Input per 1M tokens
- $0.25
- Output per 1M tokens
- $1.25
- Open weights
- No
- License
- proprietary
- Parameters
- —
- Knowledge cutoff
- Aug 2023
- Reasoning
- No
- Modalities
- text, image → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Knowledge & reasoning | 10.4 | Not ranked | 1 of 4 |
| Human preference | 20.1 | Not ranked | 2 of 5 |
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 50.1% | Third party | — | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.0884 | Third party | — | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| MMLU | Accuracy | 73.8% | Third party | — | — | Stanford CRFM Leaderboard via Epoch AI |
| ScienceQA | Accuracy | 72.0% | Self-reported | — | — | Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI |
| WinoGrande | Accuracy | 74.2% | Self-reported | — | — | The Claude 3 Model Family: Opus, Sonnet, Haiku via Epoch AI |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 36.3% | Independent | — | 27 Jan 2025 | Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| MATH Level 5 | Accuracy | 14.9% | Independent | — | 27 Jan 2025 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 1.8% | Independent | — | 25 Feb 2025 | Epoch AI |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| CadEval | Overall pass rate | 12.0% | Third party | — | — | CadEval Dashboard via Epoch AI |
| WeirdML (v2) | Average accuracy | 9.8% | Third party | — | — | https://htihle.github.io/weirdml.html via Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Text Arena (arena.ai) | Arena score (Elo scale) | 1262 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 117701 | Independent | — | 25 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1000 | Independent | — | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 13380 | Independent | — | 28 Sep 2026 | Arena |
Other Claude Haiku versions
- Claude Haiku 4.515 Oct 2025
- Claude 3.5 Haiku4 Nov 2024
Sources
- https://www.anthropic.com/news/claude-3-haiku
- https://web.archive.org/web/20241215000000/https://docs.anthropic.com/en/docs/about-claude/models
- https://web.archive.org/web/20251220000000/https://docs.claude.com/en/docs/about-claude/models/overview
- https://platform.claude.com/docs/en/about-claude/model-deprecations
- https://platform.claude.com/docs/en/release-notes/overview