Model comparison
Grok 4.20 (Non-Reasoning) vs Mercury 2
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 39.1 on the Noometry Index. Mercury 2 costs 4.2× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Summary
- They share 14 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) 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 4.20 (Non-Reasoning) leads 52.3 to 23.8.
- The biggest single-benchmark swing is WeirdML: 52.3% for Grok 4.20 (Non-Reasoning) and 43.2% for Mercury 2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 128K.
Side by side
| Grok 4.20 (Non-Reasoning) | Mercury 2 | |
|---|---|---|
| Provider | xAI | Inception |
| Noometry Index | 48.6 | 39.1 |
| Released | 2026-02-17 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 128K |
| Max output | 30K | 50K |
| Input $ / M tokens | $1.25 | $0.25 |
| Output $ / M tokens | $2.50 | $0.75 |
| Results tracked | 46 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 42.1 (#112), Mercury 2: 33.5 (#255)
| Benchmark | Grok 4.20 (Non-Reasoning) | Mercury 2 |
|---|---|---|
| LMArena WebDev | 1375 | 1171 |
| WeirdML | 52.3% | 43.2% |
| LMArena Coding | 1459 | 1391 |
| ALE-Bench | 1,150 | 785.58 |
| SciCode | — | 38.7% |
Agentic & Tool Use Not comparable
Grok 4.20 (Non-Reasoning): 34.4 (#46), Mercury 2: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Mercury 2 |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.3 (#32), Mercury 2: 23.8 (#170)
| Benchmark | Grok 4.20 (Non-Reasoning) | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1362 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 85.4% | — |
| ARC-AGI-1 | 89.5% | — |
| CritPt | — | 0.8% |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |
| DTBench | 90.1% | — |
| LMCA | 38.7% | — |
| Epoch Capabilities Index | 151.98 | — |
| ForecastBench | 61.4 | — |
Math Not comparable
Grok 4.20 (Non-Reasoning): 48.2 (#65), Mercury 2: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Mercury 2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| ProofBench | 14% | — |
| LMArena Math | 1455 | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.8 (#60), Mercury 2: 36.2 (#172)
| Benchmark | Grok 4.20 (Non-Reasoning) | Mercury 2 |
|---|---|---|
| LMArena Expert | 1439 | 1358 |
| GPQA Diamond | 89.3% | — |
| SimpleQA Verified | 30.2% | — |
| Vectara Hallucination Rate | — | 12.3% |
Multimodal Not comparable
Grok 4.20 (Non-Reasoning): 33.3 (#98), Mercury 2: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Mercury 2 |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 54.5 (#40), Mercury 2: 46.6 (#157)
| Benchmark | Grok 4.20 (Non-Reasoning) | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1441 | 1331 |
| LMArena Chinese | 1481 | 1417 |
| LMArena Russian | 1458 | 1304 |
| LMArena French | 1476 | — |
| LMArena German | 1465 | — |
| LMArena Japanese | 1449 | — |
| LMArena Korean | 1417 | — |
| LMArena Spanish | 1443 | — |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 74.8 (#83), Mercury 2: 70.2 (#165)
| Benchmark | Grok 4.20 (Non-Reasoning) | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1329 |
Long Context Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 45.5 (#34), Mercury 2: 40.5 (#154)
| Benchmark | Grok 4.20 (Non-Reasoning) | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1437 | 1330 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 65.7 (#44), Mercury 2: 53.8 (#155)
| Benchmark | Grok 4.20 (Non-Reasoning) | Mercury 2 |
|---|---|---|
| LMArena Text | 1451 | 1355 |
| LMArena Creative Writing | 1438 | 1289 |
| LMArena Multi-Turn | 1456 | 1358 |
| EQ-Bench Creative Writing | 1574 | — |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Mercury 2?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 39.1 on the Noometry Index. Mercury 2 costs 4.2× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Which is cheaper, Grok 4.20 (Non-Reasoning) or Mercury 2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.
Is Grok 4.20 (Non-Reasoning) or Mercury 2 better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 (Non-Reasoning) does, with 1M tokens against 128K.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Mercury 2 share?
14 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Mercury 2 has 17.