Claude Haiku 4.5 Pro on MMLU-Pro: score, rank and what it means
Claude Haiku 4.5 Pro scores 81.5 on MMLU-Pro, placing it #133 of 600 models in the index. The benchmark average is 73.5 and the leader is GPT-5.2 Pro at 91.6.
Score distribution
The chart shows the top 10 models on MMLU-Pro, with Claude Haiku 4.5 Pro highlighted. Longer bars mean higher scores.
Top 10 leaderboard
| # | Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|---|
| 1 | GPT-5.2 Pro | OpenAI | 2000000 | $21.32 | 89.6 |
| 2 | GPT-5.1 Max | OpenAI | 2000000 | $20.50 | 87.9 |
| 3 | Claude Opus 4.5 Pro | Anthropic | 200000 | $20.98 | 89.1 |
| 4 | Claude Opus 4.5 Reasoning | Anthropic | 2000000 | $20.91 | 88.2 |
| 5 | Gemini 3 Pro Reasoning | Google DeepMind | 200000 | $19.69 | 87.5 |
| 6 | GPT-5.1 Reasoning | OpenAI | 400000 | $20.27 | 88.3 |
| 7 | GPT-5.2 | OpenAI | 2000000 | $19.71 | 88.0 |
| 8 | Claude Opus 4.5 Max | Anthropic | 1000000 | $20.90 | 87.8 |
| 9 | GPT-5.2 Vision | OpenAI | 1000000 | $19.03 | 87.4 |
| 10 | Gemini 3 Pro Max | Google DeepMind | 2000000 | $20.57 | 87.9 |
What this score means
On MMLU-Pro, Claude Haiku 4.5 Pro sits at #133 of 600. The leader, GPT-5.2 Pro, scores 91.6, so the gap to the top is 10.1 points. The median model in this index scores 76.1, which puts Claude Haiku 4.5 Pro above the midpoint.
Anthropic models average 83.4 on this benchmark. Claude Haiku 4.5 Pro is 1.9 points below that provider line, so it is a weaker result than the average Anthropic model.
Among multimodal models, the average is 80.0. Claude Haiku 4.5 Pro is 1.5 points above that group. This is the more useful comparison if you are shortlisting within the same tier rather than across the whole index.
Read a 81.5 as a relative signal, not an absolute guarantee. Benchmark scores depend on prompt format, evaluation harness and contamination controls. Use this page to narrow the shortlist, then test the model on your own data.
Price context
At $15.07 per million input tokens, Claude Haiku 4.5 Pro is above the median input price of $4.00 across the 600 models scored on MMLU-Pro. The models immediately around it in the ranking are shown below so you can compare score and price together.
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| ERNIE 4.0 Pro | Baidu | 200000 | $12.58 | 77.5 |
| GLM-4.5 Chat | Zhipu AI | 65536 | $4.53 | 78.3 |
| ERNIE 4.0 Reasoning | Baidu | 65536 | $12.20 | 77.8 |
| Sonar Pro Turbo | Perplexity | 128000 | $13.55 | 79.0 |
| Claude Haiku 4.5 Pro | Anthropic | 1000000 | $15.07 | 80.8 |
| DeepSeek-Coder Instruct | DeepSeek | 32768 | $4.34 | 77.7 |
| MiniMax-Text Chat | MiniMax | 128000 | $4.26 | 77.8 |
Other benchmarks for Claude Haiku 4.5 Pro
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| GPQA Diamond | 75.7 | 128 | 79th | |
| SWE-bench Verified | 70.4 | 101 | 83th | |
| HumanEval | 86.0 | 101 | 83th | |
| MATH-500 | 83.7 | 131 | 78th | |
| AIME 2025 | 80.1 | 87 | 86th | |
| LiveCodeBench | 72.4 | 138 | 77th | |
| IFEval | 90.1 | 70 | 88th | |
| TruthfulQA | 84.1 | 81 | 87th | |
| HellaSwag | 89.3 | 105 | 83th | |
| MMMU | 75.3 | 157 | 74th | |
| Arena Elo | 1436.2 | 105 | 83th |
FAQ
What score does Claude Haiku 4.5 Pro get on MMLU-Pro?
Claude Haiku 4.5 Pro scores 81.5 on MMLU-Pro in this index. The benchmark average is 73.5 and the top score is 91.6.
How does Claude Haiku 4.5 Pro rank on MMLU-Pro?
It ranks #133 of 600 models, in the 78th percentile. The leader is GPT-5.2 Pro at 91.6.
Is Claude Haiku 4.5 Pro good at MMLU-Pro?
Yes, relative to the index: it is above the median and inside the top half of scores. The result should be read alongside its price and context window.
How is the MMLU-Pro score calculated?
MMLU-Pro is a knowledge benchmark. Scores in this index are modelled estimates on a 0–100 scale (or Elo for Arena), derived from capability tier and benchmark difficulty. They are not official leaderboard results.
What does Claude Haiku 4.5 Pro cost?
Claude Haiku 4.5 Pro costs $15.07 per million input tokens and $73.96 per million output tokens.