Claude 3.5 Haiku
As of 15 Nov 2026, Claude 3.5 Haiku by Anthropic scores 38.6 on the BenchLeader Index (611 ranked configurations), with its best results in human preference (48) and weakest in knowledge (30). Released 4 Nov 2024.
Key facts (as of 15 Nov 2026)
- Claude 3.5 Haiku was released on 4 Nov 2024 (Anthropic).
In detail. Claude 3.5 Haiku is an Anthropic proprietary model, released 4 Nov 2024. Its best configuration ranks #561 of 611 on the BenchLeader Index at 38.6 ±3.4, in the lower half. The ± is the point: 143 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in human preference (48) and lowest in knowledge (30). Last measured 11 Nov 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 200k
- via Artificial Analysis
- Cost per task
- –
- Tokens per task
- –
- Released
- 4 Nov 2024
- Overall index39
- Reasoning36
- Coding34
- Agents & tools36
- Maths37
- Knowledge30
- Instruction following45
- Human preference48
- Multimodal32
- Long context37
Embed this rank
More badge styles[](https://www.benchleader.com/models/claude-3-5-haiku)Paste it at the top of README.md, beside your other badges. The badge redraws with every data update and links back to this page.
Versions
Anthropic has shipped 6 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Claude Haiku 5.5xhigh | 7 Oct 2026 | 56.7 | #174 |
| Claude Haiku 4.5 | 15 Oct 2025 | 47.7 | #401 |
| Claude 3.5 Haikuthis page | 4 Nov 2024 | 38.6 | #561 |
| Claude 3 Haiku | 7 Mar 2024 | 36.2 | #582 |
| Claude Haiku 3 | – | – | – |
| Claude Haiku 4thinking | – | – | – |
How its index has moved
8 Sep 2026 to 15 Nov 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond | 38.1%#265 | Epoch AI Benchmarking Hub | |
| Arena Hard Prompts | 1346#228 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 40.8%#484 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 3.6%#604 | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | 37.9%#128 | Vals AI | |
| GPQA Diamond (HELM)not in index | 36.3%#55 | HELM Capabilities | |
| CritPtnot in index | 0.0%#337 | Artificial Analysis | |
| DTBenchnot in index | 56.7%#202 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SciCode | 27.4%#223 | SciCode | |
| WeirdML | 30.7%#135 | WeirdML | |
| Arena Coding | 1386#217 | Arena (LMArena) | |
| LiveCodeBench | 41.9%#126 | Vals AI | |
| Aider Polyglot | 28.0%#48 | Aider polyglot leaderboard | |
| CadEvalnot in index | 32.0%#10 | Epoch AI Benchmarking Hub | |
| Terminal-Bench 2.1 (AA)not in index | 10.1%#198 | Artificial Analysis | |
| LiveCodeBench (AA)not in index | 31.4%#197 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Terminal-Bench Hard | 2.3%#325 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 24.6%#305 | Artificial Analysis | |
| GDPval-AA v2.1not in index | 218#274 | Artificial Analysis | |
| BALROGnot in index | 19.3%#25 | BALROG | |
| BrowseCompnot in index | 0.3%#39 | OpenAI |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| OTIS Mock AIME | 4.3%#262 | Epoch AI Benchmarking Hub | |
| MATH Level 5 | 46.4%#58 | Epoch AI Benchmarking Hub | |
| AIME (Vals) | 3.3%#92 | Vals AI | |
| MGSM | 84.6%#67 | Vals AI | |
| Omni-MATH (HELM) | 22.4%#54 | HELM Capabilities | |
| MATH 500not in index | 64.2%#55 | Vals AI | |
| Arena Maths | 1287#247 | Arena (LMArena) |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMLU-Pro | 64.1%#128 | Vals AI | |
| LegalBench | 70.3%#122 | Vals AI | |
| CorpFin | 50.8%#104 | Vals AI | |
| TaxEval | 57.4%#133 | Vals AI | |
| MMLU-Pro (HELM)not in index | 60.5%#46 | HELM Capabilities | |
| MMLUnot in index | 74.3%#40 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 42.8%#237 | Artificial Analysis | |
| IFEval (HELM) | 79.2%#50 | HELM Capabilities | |
| WildBench (HELM) | 76.0%#49 | HELM Capabilities | |
| Arena Instruction Followingnot in index | 1316#227 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1325#237 | Arena (LMArena) | |
| EQ-Bench Creative Writing v3not in index | 1144#96 | EQ-Bench | |
| Arena Creative Writingnot in index | 1305#218 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1328#222 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1346#214 | Arena (LMArena) | |
| Lech Mazur Creative Writingnot in index | 73.5%#29 | Lech Mazur |
Multimodal
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Vision | 1092#128 | Arena (LMArena) | |
| MMMU-Pro | 45.6%#267 | Artificial Analysis | |
| GeoBenchnot in index | 34.0%#44 | GeoBench |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR v1.1 | 27.3%#429 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 124.9#158 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2not in index | 8.9#429 | Artificial Analysis | |
| AA Progress Index v1not in index | 159.6#534 | Artificial Analysis | |
| HELM Capabilities meannot in index | 54.9%#54 | HELM Capabilities |
Safety & honesty
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| FORTRESSnot in index | 30.4%#25 | Scale AI SEAL |
More from Anthropic
See also
Embed or cite
Show where Claude 3.5 Haiku ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page.
[](https://www.benchleader.com/models/claude-3-5-haiku)Cite this
The ranking changes daily, so a reference carries the data date. APA style:
BenchLeader. (2026, November 15). Claude 3.5 Haiku on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 15, 2026, from https://www.benchleader.com/models/claude-3-5-haiku
BibTeX:
@misc{benchleader_claude_3_5_haiku_20261115,
author = {{BenchLeader}},
title = {{Claude 3.5 Haiku on the BenchLeader Index (method v1.4)}},
year = {2026},
month = nov,
howpublished = {\url{https://www.benchleader.com/models/claude-3-5-haiku}},
note = {Data as of 2026-11-15}
}Every badge style, the embeddable top-10 widget and how to cite the Index
Questions people ask
- What are Claude 3.5 Haiku's benchmark scores?
- As of 15 Nov 2026, Claude 3.5 Haiku scores 38.6 ±3.4 on the BenchLeader Index, strongest in human preference (48) and weakest in knowledge (30). That rests on independent benchmark results only, and every score on this page links to its publisher.
- How does Claude 3.5 Haiku rank?
- Claude 3.5 Haiku is #561 of 611 ranked configurations on 15 Nov 2026. 143 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Fable 5.2 (max effort) at 72.7.
- When was Claude 3.5 Haiku released?
- Anthropic released Claude 3.5 Haiku on 4 Nov 2024.
Data as of 15 Nov 2026. Compare with another model.
Cite as: BenchLeader, “Claude 3.5 Haiku: benchmarks, pricing, speed and rank”, data as of 15 Nov 2026, https://www.benchleader.com/models/claude-3-5-haiku.