Model comparison
GPT-5.1 vs Mercury 2
GPT-5.1 is the stronger model overall, scoring 49.0 to 39.1 on the Noometry Index. Mercury 2 costs 9.2× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GPT-5.1 scores higher in 7 categories and Mercury 2 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.1 leads 39.8 to 23.8.
- The biggest single-benchmark swing is WeirdML: 60.8% for GPT-5.1 and 43.2% for Mercury 2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GPT-5.1 accepts more context: 400K tokens versus 128K.
Side by side
| GPT-5.1 | Mercury 2 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 49.0 | 39.1 |
| Released | 2025-11-13 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 128K |
| Max output | 128K | 50K |
| Input $ / M tokens | $1.25 | $0.25 |
| Output $ / M tokens | $10 | $0.75 |
| Results tracked | 63 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GPT-5.1: 46.4 (#66), Mercury 2: 33.5 (#255)
| Benchmark | GPT-5.1 | Mercury 2 |
|---|---|---|
| LMArena WebDev | 1395 | 1171 |
| SciCode | 43.3% | 38.7% |
| WeirdML | 60.8% | 43.2% |
| LMArena Coding | 1454 | 1391 |
| ALE-Bench | 1,192 | 785.58 |
| SWE-bench Verified | 68% | — |
| SWE-bench Verified (bash only) | 66% | — |
| GSO | 13.7% | — |
| LiveBench Coding | 72.5% | — |
Agentic & Tool Use Not comparable
GPT-5.1: 32.7 (#60), Mercury 2: —
| Benchmark | GPT-5.1 | Mercury 2 |
|---|---|---|
| Terminal-Bench | 47.6% | — |
| DeepResearch Bench | 42.8% | — |
| LMArena Search | 1199 | — |
| Vending-Bench 2 | 1,473 | — |
Reasoning GPT-5.1 leads
GPT-5.1: 39.8 (#58), Mercury 2: 23.8 (#170)
| Benchmark | GPT-5.1 | Mercury 2 |
|---|---|---|
| CritPt | 4.9% | 0.8% |
| LMArena Hard Prompts | 1457 | 1362 |
| ARC-AGI-2 | 17.6% | — |
| SimpleBench | 53.2% | — |
| ARC-AGI-1 | 72.8% | — |
| Chess Puzzles | 32% | — |
| EnigmaEval | 11.2% | — |
| LiveBench Reasoning | 95.8% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 90.1% | — |
| LiveBench Data Analysis | 72.1% | — |
| LMCA | 43.9% | — |
| Epoch Capabilities Index | 149.64 | — |
| ForecastBench | 58.1 | — |
| LiveBench | 78.8% | — |
Math Not comparable
GPT-5.1: 52.2 (#51), Mercury 2: —
| Benchmark | GPT-5.1 | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | — |
| Omni-MATH | 46.4% | — |
| LiveBench Math | 94.5% | — |
| LMArena Math | 1447 | — |
| FrontierMath (Feb 2025 set) | 31% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GPT-5.1 leads
GPT-5.1: 50.6 (#71), Mercury 2: 36.2 (#172)
| Benchmark | GPT-5.1 | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | 12.3% |
| LMArena Expert | 1470 | 1358 |
| GPQA Diamond | 87.6% | — |
| Humanity's Last Exam | 23.7% | — |
| SimpleQA Verified | 48% | — |
| MMLU-Pro | 57.9% | — |
| GPQA (HELM) | 44.2% | — |
Multimodal Not comparable
GPT-5.1: 44.8 (#19), Mercury 2: —
| Benchmark | GPT-5.1 | Mercury 2 |
|---|---|---|
| LMArena Vision | 1250 | — |
| VPCT | 58.7% | — |
| LMArena Document | 1403 | — |
Multilingual GPT-5.1 leads
GPT-5.1: 53.8 (#56), Mercury 2: 46.6 (#157)
| Benchmark | GPT-5.1 | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1431 | 1331 |
| LMArena Chinese | 1495 | 1417 |
| LMArena Russian | 1435 | 1304 |
| LMArena French | 1450 | — |
| LMArena German | 1438 | — |
| LMArena Japanese | 1453 | — |
| LMArena Korean | 1401 | — |
| LMArena Spanish | 1433 | — |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), Mercury 2: 70.2 (#165)
| Benchmark | GPT-5.1 | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1443 | 1329 |
| LiveBench Instruction Following | 93.3% | — |
| IFEval | 93.5% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), Mercury 2: 40.5 (#154)
| Benchmark | GPT-5.1 | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1447 | 1330 |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference GPT-5.1 leads
GPT-5.1: 64.5 (#55), Mercury 2: 53.8 (#155)
| Benchmark | GPT-5.1 | Mercury 2 |
|---|---|---|
| LMArena Text | 1443 | 1355 |
| LMArena Creative Writing | 1427 | 1289 |
| LMArena Multi-Turn | 1450 | 1358 |
| WildBench | 86.3% | — |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than Mercury 2?
GPT-5.1 is the stronger model overall, scoring 49.0 to 39.1 on the Noometry Index. Mercury 2 costs 9.2× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Which is cheaper, GPT-5.1 or Mercury 2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is GPT-5.1 or Mercury 2 better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1 does, with 400K tokens against 128K.
How many benchmarks do GPT-5.1 and Mercury 2 share?
17 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Mercury 2 has 17.