Model comparison
GPT-4.1 nano vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 to 27.9 on the Noometry Index. GPT-4.1 nano costs 2.1× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Summary
- They share 14 benchmarks with published results for both. GPT-4.1 nano scores higher in 0 categories and Mercury 2 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Mercury 2 leads 40.5 to 23.7.
- The biggest single-benchmark swing is WeirdML: 19% for GPT-4.1 nano and 43.2% for Mercury 2.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 128K.
Side by side
| GPT-4.1 nano | Mercury 2 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 27.9 | 39.1 |
| Released | 2025-04-14 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 128K |
| Max output | 33K | 50K |
| Input $ / M tokens | $0.10 | $0.25 |
| Output $ / M tokens | $0.40 | $0.75 |
| Results tracked | 38 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2 leads
GPT-4.1 nano: 24.1 (#330), Mercury 2: 33.5 (#255)
| Benchmark | GPT-4.1 nano | Mercury 2 |
|---|---|---|
| SciCode | 25.9% | 38.7% |
| WeirdML | 19% | 43.2% |
| LMArena Coding | 1306 | 1391 |
| Aider Polyglot | 8.9% | — |
| LMArena WebDev | — | 1171 |
| ALE-Bench | — | 785.58 |
Agentic & Tool Use Not comparable
GPT-4.1 nano: 26.5 (#104), Mercury 2: —
| Benchmark | GPT-4.1 nano | Mercury 2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | — |
Reasoning Mercury 2 leads
GPT-4.1 nano: 8.5 (#349), Mercury 2: 23.8 (#170)
| Benchmark | GPT-4.1 nano | Mercury 2 |
|---|---|---|
| CritPt | 0% | 0.8% |
| LMArena Hard Prompts | 1286 | 1362 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 33.3% | — |
| ARC-AGI-1 | 0% | — |
| DTBench | 52.5% | — |
| LMCA | 5.5% | — |
| Epoch Capabilities Index | 129.62 | — |
Math Not comparable
GPT-4.1 nano: 26.9 (#252), Mercury 2: —
| Benchmark | GPT-4.1 nano | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 28.9% | — |
| Omni-MATH | 36.7% | — |
| LMArena Math | 1274 | — |
| MATH Level 5 | 70% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge Mercury 2 leads
GPT-4.1 nano: 21.8 (#273), Mercury 2: 36.2 (#172)
| Benchmark | GPT-4.1 nano | Mercury 2 |
|---|---|---|
| LMArena Expert | 1272 | 1358 |
| GPQA Diamond | 48.9% | — |
| SimpleQA Verified | 6% | — |
| MMLU-Pro | 55% | — |
| Vectara Hallucination Rate | — | 12.3% |
| GPQA (HELM) | 50.7% | — |
Multimodal Not comparable
GPT-4.1 nano: 29.2 (#113), Mercury 2: —
| Benchmark | GPT-4.1 nano | Mercury 2 |
|---|---|---|
| LMArena Vision | 1063 | — |
Multilingual Mercury 2 leads
GPT-4.1 nano: 41.6 (#205), Mercury 2: 46.6 (#157)
| Benchmark | GPT-4.1 nano | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1260 | 1331 |
| LMArena Chinese | 1270 | 1417 |
| LMArena Russian | 1261 | 1304 |
| LMArena German | 1288 | — |
| LMArena Japanese | 1198 | — |
Instruction Following Mercury 2 leads
GPT-4.1 nano: 67.8 (#193), Mercury 2: 70.2 (#165)
| Benchmark | GPT-4.1 nano | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1267 | 1329 |
| IFEval | 84.3% | — |
Long Context Mercury 2 leads
GPT-4.1 nano: 23.7 (#296), Mercury 2: 40.5 (#154)
| Benchmark | GPT-4.1 nano | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1283 | 1330 |
| Fiction.LiveBench | 25% | — |
Writing & Preference Mercury 2 leads
GPT-4.1 nano: 40.5 (#243), Mercury 2: 53.8 (#155)
| Benchmark | GPT-4.1 nano | Mercury 2 |
|---|---|---|
| LMArena Text | 1285 | 1355 |
| LMArena Creative Writing | 1260 | 1289 |
| LMArena Multi-Turn | 1277 | 1358 |
| EQ-Bench Creative Writing | 946 | — |
| WildBench | 81.2% | — |
Frequently asked questions
Is GPT-4.1 nano better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 27.9 on the Noometry Index. GPT-4.1 nano costs 2.1× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 nano or Mercury 2?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Mercury 2 lists at $0.25 and $0.75.
Is GPT-4.1 nano or Mercury 2 better for coding?
Mercury 2 scores higher on coding benchmarks: 33.5 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 128K.
How many benchmarks do GPT-4.1 nano and Mercury 2 share?
14 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and Mercury 2 has 17.