Model comparison
Grok 4.6 vs Mercury 2
Grok 4.6 is the stronger model overall, scoring 56.8 to 38.8 on the Noometry Index. Mercury 2 costs 8.0× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. Grok 4.6 scores higher in 7 categories and Mercury 2 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.3 to 23.0.
- The biggest single-benchmark swing is WeirdML: 67.3% for Grok 4.6 and 43.2% for Mercury 2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2 / $6 for Grok 4.6.
- Grok 4.6 accepts more context: 500K tokens versus 128K.
Side by side
| Grok 4.6 | Mercury 2 | |
|---|---|---|
| Provider | xAI | Inception |
| Noometry Index | 56.8 | 38.8 |
| Released | 2026-08-12 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 500K | 128K |
| Max output | 500K | 50K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $6 | $0.75 |
| Results tracked | 49 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Grok 4.6: 58.0 (#14), Mercury 2: 33.2 (#250)
| Benchmark | Grok 4.6 | Mercury 2 |
|---|---|---|
| LMArena WebDev | 1620 | 1170 |
| SciCode | 56.5% | 38.7% |
| WeirdML | 67.3% | 43.2% |
| LMArena Coding | 1464 | 1391 |
| ALE-Bench | 1,508 | 785.58 |
| DeepSWE | 67.5% | — |
| FrontierCode | 48% | — |
| CursorBench | 41.4% | — |
| FrontierSWE | 25.3% | — |
Agentic & Tool Use Not comparable
Grok 4.6: 39.4 (#25), Mercury 2: —
| Benchmark | Grok 4.6 | Mercury 2 |
|---|---|---|
| APEX-Agents | 65.3% | — |
| GDP.pdf | 17.2% | — |
| Vending-Bench 2 | 9,047 | — |
Reasoning Grok 4.6 leads
Grok 4.6: 61.3 (#18), Mercury 2: 23.0 (#170)
| Benchmark | Grok 4.6 | Mercury 2 |
|---|---|---|
| CritPt | 19.7% | 0.8% |
| LMArena Hard Prompts | 1445 | 1362 |
| ARC-AGI-2 | 67.1% | — |
| SimpleBench | 75.9% | — |
| NYT Connections (extended) | 80% | — |
| ARC-AGI-1 | 87.5% | — |
| Chess Puzzles | 40% | — |
| EBR-Bench | 30.5% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.3% | — |
| LMCA | 48.5% | — |
| Epoch Capabilities Index | 156.48 | — |
Math Not comparable
Grok 4.6: 66.8 (#19), Mercury 2: —
| Benchmark | Grok 4.6 | Mercury 2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 31.7% | — |
| OTIS Mock AIME 2024-2025 | 99.2% | — |
| ProofBench | 51% | — |
| LMArena Math | 1416 | — |
Knowledge Grok 4.6 leads
Grok 4.6: 63.3 (#18), Mercury 2: 35.6 (#170)
| Benchmark | Grok 4.6 | Mercury 2 |
|---|---|---|
| LMArena Expert | 1463 | 1358 |
| GPQA Diamond | 94% | — |
| SimpleQA Verified | 49.3% | — |
| Vectara Hallucination Rate | — | 12.3% |
Multimodal Not comparable
Grok 4.6: 43.9 (#18), Mercury 2: —
| Benchmark | Grok 4.6 | Mercury 2 |
|---|---|---|
| LMArena Vision | 1265 | — |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
| LMArena Document | 1452 | — |
Multilingual Grok 4.6 leads
Grok 4.6: 53.3 (#67), Mercury 2: 46.8 (#153)
| Benchmark | Grok 4.6 | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1422 | 1331 |
| LMArena Chinese | 1479 | 1416 |
| LMArena Russian | 1427 | 1303 |
| LMArena French | 1458 | — |
| LMArena German | 1425 | — |
| LMArena Japanese | 1383 | — |
| LMArena Korean | 1395 | — |
| LMArena Spanish | 1408 | — |
Instruction Following Grok 4.6 leads
Grok 4.6: 75.6 (#59), Mercury 2: 70.4 (#161)
| Benchmark | Grok 4.6 | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1431 | 1328 |
Long Context Grok 4.6 leads
Grok 4.6: 44.4 (#62), Mercury 2: 40.4 (#149)
| Benchmark | Grok 4.6 | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1453 | 1329 |
Writing & Preference Grok 4.6 leads
Grok 4.6: 62.5 (#77), Mercury 2: 54.0 (#151)
| Benchmark | Grok 4.6 | Mercury 2 |
|---|---|---|
| LMArena Text | 1427 | 1355 |
| LMArena Creative Writing | 1430 | 1289 |
| LMArena Multi-Turn | 1422 | 1358 |
Frequently asked questions
Is Grok 4.6 better than Mercury 2?
Grok 4.6 is the stronger model overall, scoring 56.8 to 38.8 on the Noometry Index. Mercury 2 costs 8.0× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Which is cheaper, Grok 4.6 or Mercury 2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Grok 4.6 lists at $2 and $6.
Is Grok 4.6 or Mercury 2 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.0 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Grok 4.6 does, with 500K tokens against 128K.
How many benchmarks do Grok 4.6 and Mercury 2 share?
16 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and Mercury 2 has 17.