Model comparison
Grok-3 mini vs Mercury 2
Grok-3 mini is the stronger model overall, scoring 41.2 to 39.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Grok-3 mini scores higher in 5 categories and Mercury 2 in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mercury 2 leads 23.8 to 13.6.
Side by side
| Grok-3 mini | Mercury 2 | |
|---|---|---|
| Provider | xAI | Inception |
| Noometry Index | 41.2 | 39.1 |
| Released | 2025-04-09 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 50K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 35 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Grok-3 mini: 40.8 (#131), Mercury 2: 33.5 (#255)
| Benchmark | Grok-3 mini | Mercury 2 |
|---|---|---|
| WeirdML | 42.6% | 43.2% |
| LMArena Coding | 1379 | 1391 |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| ALE-Bench | — | 785.58 |
Reasoning Mercury 2 leads
Grok-3 mini: 13.6 (#334), Mercury 2: 23.8 (#170)
| Benchmark | Grok-3 mini | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1362 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| CritPt | — | 0.8% |
| Epoch Capabilities Index | 140.35 | — |
Math Not comparable
Grok-3 mini: 42.1 (#85), Mercury 2: —
| Benchmark | Grok-3 mini | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| LMArena Math | 1386 | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.4 (#81), Mercury 2: 36.2 (#172)
| Benchmark | Grok-3 mini | Mercury 2 |
|---|---|---|
| LMArena Expert | 1395 | 1358 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| Vectara Hallucination Rate | — | 12.3% |
| GPQA (HELM) | 67.5% | — |
Multilingual Grok-3 mini leads
Grok-3 mini: 48.1 (#145), Mercury 2: 46.6 (#157)
| Benchmark | Grok-3 mini | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1352 | 1331 |
| LMArena Chinese | 1387 | 1417 |
| LMArena Russian | 1353 | 1304 |
| LMArena French | 1357 | — |
| LMArena German | 1349 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1335 | — |
| LMArena Spanish | 1381 | — |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), Mercury 2: 70.2 (#165)
| Benchmark | Grok-3 mini | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1357 | 1329 |
| IFEval | 95.1% | — |
Long Context Too close to call
Grok-3 mini: 41.0 (#147), Mercury 2: 40.5 (#154)
| Benchmark | Grok-3 mini | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1372 | 1330 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Mercury 2 leads
Grok-3 mini: 52.5 (#169), Mercury 2: 53.8 (#155)
| Benchmark | Grok-3 mini | Mercury 2 |
|---|---|---|
| LMArena Text | 1370 | 1355 |
| LMArena Creative Writing | 1342 | 1289 |
| LMArena Multi-Turn | 1355 | 1358 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Mercury 2?
Grok-3 mini is the stronger model overall, scoring 41.2 to 39.1 on the Noometry Index.
Is Grok-3 mini or Mercury 2 better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 33.5 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Mercury 2 share?
12 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Mercury 2 has 17.