OLMo 2 Instruct on GPQA Diamond: score, rank and what it means
OLMo 2 Instruct scores 67.0 on GPQA Diamond, placing it #330 of 600 models in the index. The benchmark average is 65.6 and the leader is GPT-5.2 Reasoning at 87.0.
Score distribution
The chart shows the top 10 models on GPQA Diamond, with OLMo 2 Instruct highlighted. Longer bars mean higher scores.
Top 10 leaderboard
| # | Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|---|
| 1 | GPT-5.2 Reasoning | OpenAI | 1000000 | $20.98 | 87.5 |
| 2 | GPT-5.1 Max | OpenAI | 2000000 | $20.50 | 87.9 |
| 3 | Claude Opus 4.5 Pro | Anthropic | 200000 | $20.98 | 89.1 |
| 4 | GPT-5.1 Reasoning | OpenAI | 400000 | $20.27 | 88.3 |
| 5 | Claude Sonnet 4.5 Reasoning | Anthropic | 400000 | $19.48 | 87.7 |
| 6 | GPT-5.2 | OpenAI | 2000000 | $19.71 | 88.0 |
| 7 | o4 Turbo | OpenAI | 2000000 | $19.34 | 86.6 |
| 8 | Claude Opus 4.5 Max | Anthropic | 1000000 | $20.90 | 87.8 |
| 9 | Grok 4 Turbo | xAI | 1000000 | $19.21 | 86.7 |
| 10 | Claude Sonnet 4.5 Max | Anthropic | 1000000 | $19.90 | 87.2 |
What this score means
On GPQA Diamond, OLMo 2 Instruct sits at #330 of 600. The leader, GPT-5.2 Reasoning, scores 87.0, so the gap to the top is 20.0 points. The median model in this index scores 68.8, which puts OLMo 2 Instruct below the midpoint.
Allen Institute for AI models average 55.6 on this benchmark. OLMo 2 Instruct is 11.4 points above that provider line, so it is a stronger result than the average Allen Institute for AI model.
Among open-weight models, the average is 63.6. OLMo 2 Instruct is 3.4 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 67.0 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 $3.03 per million input tokens, OLMo 2 Instruct is below the median input price of $4.00 across the 600 models scored on GPQA Diamond. 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 |
|---|---|---|---|---|
| Nova Lite Pro | Amazon | 200000 | $9.69 | 74.1 |
| o4 Nano | OpenAI | 65536 | $8.61 | 72.0 |
| Mixtral Turbo Chat | Together AI | 32768 | $3.02 | 71.7 |
| Doubao 1.5 Pro Mini | ByteDance | 32768 | $8.30 | 72.3 |
| OLMo 2 Instruct | Allen Institute for AI | 32768 | $3.03 | 71.7 |
| Phi-3.5 | Microsoft | 16384 | $2.81 | 70.9 |
| Llama 3.1 Cerebras Base | Cerebras | 65536 | $3.36 | 72.7 |
Other benchmarks for OLMo 2 Instruct
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 75.5 | 319 | 47th | |
| SWE-bench Verified | 61.0 | 300 | 50th | |
| HumanEval | 76.6 | 318 | 47th | |
| MATH-500 | 72.2 | 365 | 39th | |
| AIME 2025 | 64.7 | 342 | 43th | |
| LiveCodeBench | 63.9 | 324 | 46th | |
| IFEval | 80.4 | 326 | 46th | |
| TruthfulQA | 73.5 | 365 | 39th | |
| HellaSwag | 84.1 | 280 | 53th | |
| MMMU | 70.3 | 288 | 52th | |
| Arena Elo | 1369.4 | 320 | 47th |
FAQ
What score does OLMo 2 Instruct get on GPQA Diamond?
OLMo 2 Instruct scores 67.0 on GPQA Diamond in this index. The benchmark average is 65.6 and the top score is 87.0.
How does OLMo 2 Instruct rank on GPQA Diamond?
It ranks #330 of 600 models, in the 45th percentile. The leader is GPT-5.2 Reasoning at 87.0.
Is OLMo 2 Instruct good at GPQA Diamond?
It is below the median for this benchmark, so test it carefully before relying on it for this capability. The result should be read alongside its price and context window.
How is the GPQA Diamond score calculated?
GPQA Diamond is a reasoning 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 OLMo 2 Instruct cost?
OLMo 2 Instruct costs $3.03 per million input tokens and $14.45 per million output tokens.