Model comparison
GPT-5 Mini vs Mercury 2
GPT-5 Mini is the stronger model overall, scoring 41.7 to 38.8 on the Noometry Index. Mercury 2 costs 1.8× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. GPT-5 Mini scores higher in 7 categories and Mercury 2 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Mini leads 45.5 to 35.6.
- The biggest single-benchmark swing is WeirdML: 52.7% for GPT-5 Mini and 43.2% for Mercury 2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
- GPT-5 Mini accepts more context: 400K tokens versus 128K.
Side by side
| GPT-5 Mini | Mercury 2 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 41.7 | 38.8 |
| Released | 2025-08-07 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 128K |
| Max output | 128K | 50K |
| Input $ / M tokens | $0.25 | $0.25 |
| Output $ / M tokens | $2 | $0.75 |
| Results tracked | 60 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
GPT-5 Mini: 40.0 (#134), Mercury 2: 33.2 (#250)
| Benchmark | GPT-5 Mini | Mercury 2 |
|---|---|---|
| SciCode | 39.2% | 38.7% |
| WeirdML | 52.7% | 43.2% |
| LMArena Coding | 1406 | 1391 |
| ALE-Bench | 799.77 | 785.58 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| LMArena WebDev | — | 1170 |
| SWE-bench Multilingual | 39.7% | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use Not comparable
GPT-5 Mini: 31.0 (#64), Mercury 2: —
| Benchmark | GPT-5 Mini | Mercury 2 |
|---|---|---|
| Terminal-Bench | 34.8% | — |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning GPT-5 Mini leads
GPT-5 Mini: 24.1 (#153), Mercury 2: 23.0 (#170)
| Benchmark | GPT-5 Mini | Mercury 2 |
|---|---|---|
| CritPt | 0% | 0.8% |
| LMArena Hard Prompts | 1380 | 1362 |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 54.3% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| Mystery Game Puzzles | 10% | — |
| DTBench | 80.5% | — |
| LMCA | 34.2% | — |
| Epoch Capabilities Index | 145.51 | — |
| ForecastBench | 61 | — |
Math Not comparable
GPT-5 Mini: 46.3 (#59), Mercury 2: —
| Benchmark | GPT-5 Mini | Mercury 2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| LMArena Math | 1377 | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.5 (#80), Mercury 2: 35.6 (#170)
| Benchmark | GPT-5 Mini | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | 12.9% | 12.3% |
| LMArena Expert | 1377 | 1358 |
| GPQA Diamond | 75% | — |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| GPQA (HELM) | 75.6% | — |
Multimodal Not comparable
GPT-5 Mini: 35.0 (#80), Mercury 2: —
| Benchmark | GPT-5 Mini | Mercury 2 |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual GPT-5 Mini leads
GPT-5 Mini: 49.1 (#131), Mercury 2: 46.8 (#153)
| Benchmark | GPT-5 Mini | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1363 | 1331 |
| LMArena Chinese | 1387 | 1416 |
| LMArena Russian | 1362 | 1303 |
| LMArena French | 1385 | — |
| LMArena German | 1366 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1306 | — |
| LMArena Spanish | 1355 | — |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.4 (#43), Mercury 2: 70.4 (#161)
| Benchmark | GPT-5 Mini | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1357 | 1328 |
| IFEval | 92.7% | — |
Long Context GPT-5 Mini leads
GPT-5 Mini: 41.9 (#127), Mercury 2: 40.4 (#149)
| Benchmark | GPT-5 Mini | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1355 | 1329 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference GPT-5 Mini leads
GPT-5 Mini: 55.4 (#143), Mercury 2: 54.0 (#151)
| Benchmark | GPT-5 Mini | Mercury 2 |
|---|---|---|
| LMArena Text | 1373 | 1355 |
| LMArena Creative Writing | 1325 | 1289 |
| LMArena Multi-Turn | 1363 | 1358 |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
Frequently asked questions
Is GPT-5 Mini better than Mercury 2?
GPT-5 Mini is the stronger model overall, scoring 41.7 to 38.8 on the Noometry Index. Mercury 2 costs 1.8× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Mini or Mercury 2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-5 Mini lists at $0.25 and $2.
Is GPT-5 Mini or Mercury 2 better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.0 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Mini does, with 400K tokens against 128K.
How many benchmarks do GPT-5 Mini and Mercury 2 share?
16 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Mercury 2 has 17.