Model comparison
GPT-4.1 vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 to 35.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
Summary
- They share 14 benchmarks with published results for both. GPT-4.1 scores higher in 5 categories and Mercury 2 in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mercury 2 leads 23.8 to 11.7.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.6% for GPT-4.1 and 12.3% for Mercury 2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 128K.
Side by side
| GPT-4.1 | Mercury 2 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 35.9 | 39.1 |
| Released | 2025-04-14 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 128K |
| Max output | 33K | 50K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $8 | $0.75 |
| Results tracked | 52 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.1: 34.4 (#238), Mercury 2: 33.5 (#255)
| Benchmark | GPT-4.1 | Mercury 2 |
|---|---|---|
| WeirdML | 39% | 43.2% |
| LMArena Coding | 1391 | 1391 |
| ALE-Bench | 558.1 | 785.58 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| CadEval | 42% | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.7 (#43), Mercury 2: —
| Benchmark | GPT-4.1 | Mercury 2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning Mercury 2 leads
GPT-4.1: 11.7 (#339), Mercury 2: 23.8 (#170)
| Benchmark | GPT-4.1 | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1362 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 0.8% |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| DTBench | 68.3% | — |
| LMCA | 25.6% | — |
| Epoch Capabilities Index | 136.78 | — |
| ForecastBench | 61.5 | — |
Math Not comparable
GPT-4.1: 22.3 (#280), Mercury 2: —
| Benchmark | GPT-4.1 | Mercury 2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6% | — |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| Omni-MATH | 47.1% | — |
| LMArena Math | 1370 | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Too close to call
GPT-4.1: 37.1 (#160), Mercury 2: 36.2 (#172)
| Benchmark | GPT-4.1 | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | 5.6% | 12.3% |
| LMArena Expert | 1364 | 1358 |
| GPQA Diamond | 66.9% | — |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), Mercury 2: —
| Benchmark | GPT-4.1 | Mercury 2 |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual GPT-4.1 leads
GPT-4.1: 49.4 (#133), Mercury 2: 46.6 (#157)
| Benchmark | GPT-4.1 | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1370 | 1331 |
| LMArena Chinese | 1382 | 1417 |
| LMArena Russian | 1377 | 1304 |
| LMArena French | 1382 | — |
| LMArena German | 1381 | — |
| LMArena Japanese | 1319 | — |
| LMArena Korean | 1339 | — |
| LMArena Spanish | 1376 | — |
Instruction Following GPT-4.1 leads
GPT-4.1: 71.3 (#153), Mercury 2: 70.2 (#165)
| Benchmark | GPT-4.1 | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1367 | 1329 |
| IFEval | 83.8% | — |
Long Context Too close to call
GPT-4.1: 40.0 (#163), Mercury 2: 40.5 (#154)
| Benchmark | GPT-4.1 | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1385 | 1330 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.6 (#125), Mercury 2: 53.8 (#155)
| Benchmark | GPT-4.1 | Mercury 2 |
|---|---|---|
| LMArena Text | 1383 | 1355 |
| LMArena Creative Writing | 1363 | 1289 |
| LMArena Multi-Turn | 1398 | 1358 |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 35.9 on the Noometry Index.
Which is cheaper, GPT-4.1 or Mercury 2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Mercury 2 better for coding?
They score almost the same on coding (34.4 vs 33.5); test both on your own repository before choosing.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 128K.
How many benchmarks do GPT-4.1 and Mercury 2 share?
14 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Mercury 2 has 17.