Model comparison
Mercury 2.5 vs o3-pro
o3-pro has enough public results to be ranked (#94); Mercury 2.5 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Summary
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $20 / $80 for o3-pro.
- Mercury 2.5 accepts more context: 260K tokens versus 200K.
Side by side
| Mercury 2.5 | o3-pro | |
|---|---|---|
| Provider | Inception | OpenAI |
| Noometry Index | 30.2 | 42.7 |
| Released | 2026-09-08 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | 260K | 200K |
| Max output | 66K | 100K |
| Input $ / M tokens | $0.04 | $20 |
| Output $ / M tokens | $0.15 | $80 |
| Results tracked | 2 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mercury 2.5: —, o3-pro: 55.1 (#22)
| Benchmark | Mercury 2.5 | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| WeirdML | — | 58.2% |
| ALE-Bench | 301.65 | — |
Reasoning Not comparable
Mercury 2.5: —, o3-pro: 24.1 (#152)
| Benchmark | Mercury 2.5 | o3-pro |
|---|---|---|
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 72.1% |
| ARC-AGI-1 | — | 59.3% |
| DTBench | — | 86.9% |
| LMCA | — | 38.5% |
| Epoch Capabilities Index | — | 147.43 |
Math Not comparable
Mercury 2.5: 22.4, o3-pro: —
| Benchmark | Mercury 2.5 | o3-pro |
|---|---|---|
| ProofBench | 3% | — |
Knowledge Not comparable
Mercury 2.5: —, o3-pro: 29.0 (#234)
| Benchmark | Mercury 2.5 | o3-pro |
|---|---|---|
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
Long Context Not comparable
Mercury 2.5: —, o3-pro: 72.1 (#1)
| Benchmark | Mercury 2.5 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
Writing & Preference Not comparable
Mercury 2.5: —, o3-pro: 57.1 (#128)
| Benchmark | Mercury 2.5 | o3-pro |
|---|---|---|
| Short-Story Creative Writing | — | 84.4% |
Frequently asked questions
Is Mercury 2.5 better than o3-pro?
o3-pro has enough public results to be ranked (#94); Mercury 2.5 does not yet, so treat this comparison as directional.
Which is cheaper, Mercury 2.5 or o3-pro?
Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; o3-pro lists at $20 and $80.
Which has the bigger context window?
Mercury 2.5 does, with 260K tokens against 200K.
How many benchmarks do Mercury 2.5 and o3-pro share?
0 benchmarks have published results for both models. Mercury 2.5 has 2 scored results on Noometry and o3-pro has 12.