Model comparison
GPT-5 Pro vs Mercury 2
GPT-5 Pro is the stronger model overall, scoring 46.4 to 39.1 on the Noometry Index. Mercury 2 costs 110× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Summary
- They share 1 benchmark with published results for both. GPT-5 Pro scores higher in 3 categories and Mercury 2 in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Pro leads 56.7 to 36.2.
- The biggest single-benchmark swing is WeirdML: 60.4% for GPT-5 Pro and 43.2% for Mercury 2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
- GPT-5 Pro accepts more context: 400K tokens versus 128K.
Side by side
| GPT-5 Pro | Mercury 2 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 46.4 | 39.1 |
| Released | 2025-10-06 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 128K |
| Max output | 272K | 50K |
| Input $ / M tokens | $15 | $0.25 |
| Output $ / M tokens | $120 | $0.75 |
| Results tracked | 12 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Pro leads
GPT-5 Pro: 44.0 (#80), Mercury 2: 33.5 (#255)
| Benchmark | GPT-5 Pro | Mercury 2 |
|---|---|---|
| WeirdML | 60.4% | 43.2% |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| LMArena Coding | — | 1391 |
| ALE-Bench | — | 785.58 |
| AlgoTune | 1.31 | — |
Reasoning GPT-5 Pro leads
GPT-5 Pro: 38.9 (#62), Mercury 2: 23.8 (#170)
| Benchmark | GPT-5 Pro | Mercury 2 |
|---|---|---|
| ARC-AGI-2 | 18.3% | — |
| SimpleBench | 61.6% | — |
| Kagi LLM Benchmark | 76.8% | — |
| ARC-AGI-1 | 70.2% | — |
| CritPt | — | 0.8% |
| EnigmaEval | 18.8% | — |
| LMArena Hard Prompts | — | 1362 |
| Epoch Capabilities Index | 150.28 | — |
Math Not comparable
GPT-5 Pro: 48.5 (#63), Mercury 2: —
| Benchmark | GPT-5 Pro | Mercury 2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 19.5% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge GPT-5 Pro leads
GPT-5 Pro: 56.7 (#42), Mercury 2: 36.2 (#172)
| Benchmark | GPT-5 Pro | Mercury 2 |
|---|---|---|
| Humanity's Last Exam | 31.6% | — |
| Vectara Hallucination Rate | — | 12.3% |
| LMArena Expert | — | 1358 |
Multilingual Not comparable
GPT-5 Pro: —, Mercury 2: 46.6 (#157)
| Benchmark | GPT-5 Pro | Mercury 2 |
|---|---|---|
| LMArena Non-English | — | 1331 |
| LMArena Chinese | — | 1417 |
| LMArena Russian | — | 1304 |
Instruction Following Not comparable
GPT-5 Pro: —, Mercury 2: 70.2 (#165)
| Benchmark | GPT-5 Pro | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | — | 1329 |
Long Context Not comparable
GPT-5 Pro: —, Mercury 2: 40.5 (#154)
| Benchmark | GPT-5 Pro | Mercury 2 |
|---|---|---|
| LMArena Longer Query | — | 1330 |
Writing & Preference Not comparable
GPT-5 Pro: —, Mercury 2: 53.8 (#155)
| Benchmark | GPT-5 Pro | Mercury 2 |
|---|---|---|
| LMArena Text | — | 1355 |
| LMArena Creative Writing | — | 1289 |
| LMArena Multi-Turn | — | 1358 |
Frequently asked questions
Is GPT-5 Pro better than Mercury 2?
GPT-5 Pro is the stronger model overall, scoring 46.4 to 39.1 on the Noometry Index. Mercury 2 costs 110× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Pro or Mercury 2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-5 Pro lists at $15 and $120.
Is GPT-5 Pro or Mercury 2 better for coding?
GPT-5 Pro scores higher on coding benchmarks: 44.0 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Pro does, with 400K tokens against 128K.
How many benchmarks do GPT-5 Pro and Mercury 2 share?
1 benchmark has published results for both models. GPT-5 Pro has 12 scored results on Noometry and Mercury 2 has 17.