Model comparison
Mercury 2 vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 39.1 on the Noometry Index. Mercury 2 costs 5.1× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
Summary
- They share 15 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and o4-mini in 7 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where o4-mini leads 40.9 to 33.5.
- The biggest single-benchmark swing is WeirdML: 43.2% for Mercury 2 and 52.6% for o4-mini.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- o4-mini accepts more context: 200K tokens versus 128K.
Side by side
| Mercury 2 | o4-mini | |
|---|---|---|
| Provider | Inception | OpenAI |
| Noometry Index | 39.1 | 41.6 |
| Released | 2026-02-20 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 200K |
| Max output | 50K | 100K |
| Input $ / M tokens | $0.25 | $1.10 |
| Output $ / M tokens | $0.75 | $4.40 |
| Results tracked | 17 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Mercury 2: 33.5 (#255), o4-mini: 40.9 (#127)
| Benchmark | Mercury 2 | o4-mini |
|---|---|---|
| WeirdML | 43.2% | 52.6% |
| LMArena Coding | 1391 | 1368 |
| ALE-Bench | 785.58 | 826.17 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| LMArena WebDev | 1171 | — |
| SciCode | 38.7% | — |
| GSO | — | 3.6% |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Not comparable
Mercury 2: —, o4-mini: 32.6 (#61)
| Benchmark | Mercury 2 | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning Too close to call
Mercury 2: 23.8 (#170), o4-mini: 24.6 (#162)
| Benchmark | Mercury 2 | o4-mini |
|---|---|---|
| CritPt | 0.8% | 0.6% |
| LMArena Hard Prompts | 1362 | 1351 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 58.7% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 77.6% |
| LMCA | — | 26.5% |
| Epoch Capabilities Index | — | 145.64 |
| ForecastBench | — | 61.8 |
Math Not comparable
Mercury 2: —, o4-mini: 40.8 (#89)
| Benchmark | Mercury 2 | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 81.7% |
| Omni-MATH | — | 72% |
| LMArena Math | — | 1389 |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Mercury 2: 36.2 (#172), o4-mini: 43.6 (#91)
| Benchmark | Mercury 2 | o4-mini |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | 18.6% |
| LMArena Expert | 1358 | 1343 |
| GPQA Diamond | — | 79.6% |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| GPQA (HELM) | — | 73.5% |
Multimodal Not comparable
Mercury 2: —, o4-mini: 40.2 (#49)
| Benchmark | Mercury 2 | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual Too close to call
Mercury 2: 46.6 (#157), o4-mini: 47.0 (#154)
| Benchmark | Mercury 2 | o4-mini |
|---|---|---|
| LMArena Non-English | 1331 | 1337 |
| LMArena Chinese | 1417 | 1354 |
| LMArena Russian | 1304 | 1334 |
| LMArena French | — | 1364 |
| LMArena German | — | 1336 |
| LMArena Japanese | — | 1308 |
| LMArena Korean | — | 1312 |
| LMArena Spanish | — | 1347 |
Instruction Following o4-mini leads
Mercury 2: 70.2 (#165), o4-mini: 75.2 (#68)
| Benchmark | Mercury 2 | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1329 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
Mercury 2: 40.5 (#154), o4-mini: 45.5 (#33)
| Benchmark | Mercury 2 | o4-mini |
|---|---|---|
| LMArena Longer Query | 1330 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Too close to call
Mercury 2: 53.8 (#155), o4-mini: 54.0 (#152)
| Benchmark | Mercury 2 | o4-mini |
|---|---|---|
| LMArena Text | 1355 | 1353 |
| LMArena Creative Writing | 1289 | 1294 |
| LMArena Multi-Turn | 1358 | 1350 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
Frequently asked questions
Is Mercury 2 better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 39.1 on the Noometry Index. Mercury 2 costs 5.1× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.
Which is cheaper, Mercury 2 or o4-mini?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is Mercury 2 or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
o4-mini does, with 200K tokens against 128K.
How many benchmarks do Mercury 2 and o4-mini share?
15 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and o4-mini has 60.