Model comparison
GPT-5 Nano vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 to 33.5 on the Noometry Index. GPT-5 Nano costs 2.7× 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-5 Nano scores higher in 2 categories and Mercury 2 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 53.8 to 39.1.
- The biggest single-benchmark swing is WeirdML: 38.1% for GPT-5 Nano and 43.2% for Mercury 2.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- GPT-5 Nano accepts more context: 400K tokens versus 128K.
Side by side
| GPT-5 Nano | Mercury 2 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 33.5 | 39.1 |
| Released | 2025-08-07 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 128K |
| Max output | 128K | 50K |
| Input $ / M tokens | $0.05 | $0.25 |
| Output $ / M tokens | $0.40 | $0.75 |
| Results tracked | 49 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5 Nano: 33.6 (#254), Mercury 2: 33.5 (#255)
| Benchmark | GPT-5 Nano | Mercury 2 |
|---|---|---|
| WeirdML | 38.1% | 43.2% |
| LMArena Coding | 1351 | 1391 |
| ALE-Bench | 718.67 | 785.58 |
| SWE-bench Verified (bash only) | 34.8% | — |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), Mercury 2: —
| Benchmark | GPT-5 Nano | Mercury 2 |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning Mercury 2 leads
GPT-5 Nano: 16.3 (#306), Mercury 2: 23.8 (#170)
| Benchmark | GPT-5 Nano | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1328 | 1362 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| CritPt | — | 0.8% |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| Epoch Capabilities Index | 139.38 | — |
| ForecastBench | 59.1 | — |
Math Not comparable
GPT-5 Nano: 29.4 (#241), Mercury 2: —
| Benchmark | GPT-5 Nano | Mercury 2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| LMArena Math | 1317 | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Too close to call
GPT-5 Nano: 35.9 (#178), Mercury 2: 36.2 (#172)
| Benchmark | GPT-5 Nano | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | 10.5% | 12.3% |
| LMArena Expert | 1321 | 1358 |
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| GPQA (HELM) | 67.9% | — |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), Mercury 2: —
| Benchmark | GPT-5 Nano | Mercury 2 |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual Mercury 2 leads
GPT-5 Nano: 45.3 (#172), Mercury 2: 46.6 (#157)
| Benchmark | GPT-5 Nano | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1313 | 1331 |
| LMArena Chinese | 1356 | 1417 |
| LMArena Russian | 1296 | 1304 |
| LMArena German | 1327 | — |
| LMArena Japanese | 1226 | — |
| LMArena Korean | 1269 | — |
| LMArena Spanish | 1360 | — |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.0 (#79), Mercury 2: 70.2 (#165)
| Benchmark | GPT-5 Nano | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1306 | 1329 |
| IFEval | 93.2% | — |
Long Context Mercury 2 leads
GPT-5 Nano: 31.3 (#281), Mercury 2: 40.5 (#154)
| Benchmark | GPT-5 Nano | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1312 | 1330 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Mercury 2 leads
GPT-5 Nano: 39.1 (#249), Mercury 2: 53.8 (#155)
| Benchmark | GPT-5 Nano | Mercury 2 |
|---|---|---|
| LMArena Text | 1320 | 1355 |
| LMArena Creative Writing | 1249 | 1289 |
| LMArena Multi-Turn | 1311 | 1358 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 33.5 on the Noometry Index. GPT-5 Nano costs 2.7× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Nano or Mercury 2?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Mercury 2 lists at $0.25 and $0.75.
Is GPT-5 Nano or Mercury 2 better for coding?
They score almost the same on coding (33.6 vs 33.5); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 128K.
How many benchmarks do GPT-5 Nano and Mercury 2 share?
14 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Mercury 2 has 17.