Model comparison
GPT-4o mini vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 to 25.5 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and Mercury 2 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mercury 2 leads 36.2 to 17.7.
- The biggest single-benchmark swing is WeirdML: 11.8% for GPT-4o mini and 43.2% for Mercury 2.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
Side by side
| GPT-4o mini | Mercury 2 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 25.5 | 39.1 |
| Released | 2024-07-18 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 128K |
| Max output | 16K | 50K |
| Input $ / M tokens | $0.15 | $0.25 |
| Output $ / M tokens | $0.60 | $0.75 |
| Results tracked | 60 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2 leads
GPT-4o mini: 22.0 (#335), Mercury 2: 33.5 (#255)
| Benchmark | GPT-4o mini | Mercury 2 |
|---|---|---|
| WeirdML | 11.8% | 43.2% |
| LMArena Coding | 1290 | 1391 |
| Aider Polyglot | 3.6% | — |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 785.58 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Not comparable
GPT-4o mini: 27.5 (#101), Mercury 2: —
| Benchmark | GPT-4o mini | Mercury 2 |
|---|---|---|
| BALROG | 17.4% | — |
Reasoning Mercury 2 leads
GPT-4o mini: 8.7 (#347), Mercury 2: 23.8 (#170)
| Benchmark | GPT-4o mini | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1362 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| CritPt | — | 0.8% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| Epoch Capabilities Index | 126.56 | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math Not comparable
GPT-4o mini: 10.4 (#314), Mercury 2: —
| Benchmark | GPT-4o mini | Mercury 2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.9% | — |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| LMArena Math | 1267 | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |
Knowledge Mercury 2 leads
GPT-4o mini: 17.7 (#284), Mercury 2: 36.2 (#172)
| Benchmark | GPT-4o mini | Mercury 2 |
|---|---|---|
| LMArena Expert | 1235 | 1358 |
| GPQA Diamond | 37.7% | — |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| Vectara Hallucination Rate | — | 12.3% |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), Mercury 2: —
| Benchmark | GPT-4o mini | Mercury 2 |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual Mercury 2 leads
GPT-4o mini: 42.0 (#199), Mercury 2: 46.6 (#157)
| Benchmark | GPT-4o mini | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1266 | 1331 |
| LMArena Chinese | 1265 | 1417 |
| LMArena Russian | 1275 | 1304 |
| LMArena French | 1297 | — |
| LMArena German | 1272 | — |
| LMArena Japanese | 1216 | — |
| LMArena Korean | 1195 | — |
| LMArena Spanish | 1276 | — |
Instruction Following Mercury 2 leads
GPT-4o mini: 61.9 (#239), Mercury 2: 70.2 (#165)
| Benchmark | GPT-4o mini | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1258 | 1329 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
Long Context Mercury 2 leads
GPT-4o mini: 39.1 (#186), Mercury 2: 40.5 (#154)
| Benchmark | GPT-4o mini | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1289 | 1330 |
Writing & Preference Mercury 2 leads
GPT-4o mini: 39.5 (#248), Mercury 2: 53.8 (#155)
| Benchmark | GPT-4o mini | Mercury 2 |
|---|---|---|
| LMArena Text | 1286 | 1355 |
| LMArena Creative Writing | 1268 | 1289 |
| LMArena Multi-Turn | 1285 | 1358 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 25.5 on the Noometry Index.
Which is cheaper, GPT-4o mini or Mercury 2?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Mercury 2 lists at $0.25 and $0.75.
Is GPT-4o mini or Mercury 2 better for coding?
Mercury 2 scores higher on coding benchmarks: 33.5 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do GPT-4o mini and Mercury 2 share?
12 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Mercury 2 has 17.