Model comparison
GPT-6.1 Sol vs Grok 4.20 (Non-Reasoning)
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 48.6 on the Noometry Index. Grok 4.20 (Non-Reasoning) costs 2.6× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. GPT-6.1 Sol scores higher in 7 categories and Grok 4.20 (Non-Reasoning) in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 48.2.
- The biggest single-benchmark swing is ProofBench: 99% for GPT-6.1 Sol and 14% for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-6.1 Sol | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 65.6 | 48.6 |
| Released | 2026-09-29 | 2026-02-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 128K | 30K |
| Input $ / M tokens | $2 | $1.25 |
| Output $ / M tokens | $10 | $2.50 |
| Results tracked | 34 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
GPT-6.1 Sol: 63.2 (#8), Grok 4.20 (Non-Reasoning): 42.1 (#112)
| Benchmark | GPT-6.1 Sol | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena WebDev | 1755 | 1375 |
| LMArena Coding | 1487 | 1459 |
| DeepSWE | 75.2% | — |
| FrontierCode | 50.2% | — |
| SciCode | 55.8% | — |
| WeirdML | — | 52.3% |
| ALE-Bench | — | 1,150 |
Agentic & Tool Use GPT-6.1 Sol leads
GPT-6.1 Sol: 39.6 (#26), Grok 4.20 (Non-Reasoning): 34.4 (#46)
| Benchmark | GPT-6.1 Sol | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| APEX-Agents | 60% | — |
| τ²-bench Banking | — | 18% |
| GDP.pdf | 32% | — |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |
Reasoning GPT-6.1 Sol leads
GPT-6.1 Sol: 81.9 (#2), Grok 4.20 (Non-Reasoning): 52.3 (#32)
| Benchmark | GPT-6.1 Sol | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| ARC-AGI-2 | 94.2% | 65.1% |
| NYT Connections (extended) | 95.5% | 85.4% |
| ARC-AGI-1 | 98.5% | 89.5% |
| Chess Puzzles | 61% | 24% |
| LMArena Hard Prompts | 1466 | 1451 |
| Epoch Capabilities Index | 166.09 | 151.98 |
| Kagi LLM Benchmark | — | 75% |
| CritPt | 31.7% | — |
| Thematic Generalization | — | 63.8% |
| EBR-Bench | 54.3% | — |
| Mystery Game Puzzles | 80% | — |
| DTBench | — | 90.1% |
| LMCA | — | 38.7% |
| ForecastBench | — | 61.4 |
Math GPT-6.1 Sol leads
GPT-6.1 Sol: 93.7 (#1), Grok 4.20 (Non-Reasoning): 48.2 (#65)
| Benchmark | GPT-6.1 Sol | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | 93.7% | 44.9% |
| FrontierMath Tier 4 | 100% | 17.1% |
| OTIS Mock AIME 2024-2025 | 100% | 92.2% |
| ProofBench | 99% | 14% |
| LMArena Math | 1464 | 1455 |
Knowledge GPT-6.1 Sol leads
GPT-6.1 Sol: 71.8 (#4), Grok 4.20 (Non-Reasoning): 52.8 (#60)
| Benchmark | GPT-6.1 Sol | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 95.4% | 89.3% |
| SimpleQA Verified | 73.9% | 30.2% |
| LMArena Expert | 1502 | 1439 |
Multimodal GPT-6.1 Sol leads
GPT-6.1 Sol: 52.7 (#5), Grok 4.20 (Non-Reasoning): 33.3 (#98)
| Benchmark | GPT-6.1 Sol | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1288 | 1263 |
| Blueprint-Bench 2 | — | 0% |
| Furniture Assembly | 80% | — |
| LMArena Document | — | 1416 |
Multilingual Too close to call
GPT-6.1 Sol: 54.3 (#46), Grok 4.20 (Non-Reasoning): 54.5 (#40)
| Benchmark | GPT-6.1 Sol | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1438 | 1441 |
| LMArena Chinese | 1477 | 1481 |
| LMArena Russian | 1455 | 1458 |
| LMArena French | — | 1476 |
| LMArena German | — | 1465 |
| LMArena Japanese | — | 1449 |
| LMArena Korean | — | 1417 |
| LMArena Spanish | — | 1443 |
Instruction Following GPT-6.1 Sol leads
GPT-6.1 Sol: 77.0 (#29), Grok 4.20 (Non-Reasoning): 74.8 (#83)
| Benchmark | GPT-6.1 Sol | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1468 | 1420 |
Long Context Too close to call
GPT-6.1 Sol: 44.9 (#54), Grok 4.20 (Non-Reasoning): 45.5 (#34)
| Benchmark | GPT-6.1 Sol | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1465 | 1437 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
GPT-6.1 Sol: 63.6 (#63), Grok 4.20 (Non-Reasoning): 65.7 (#44)
| Benchmark | GPT-6.1 Sol | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1447 | 1451 |
| LMArena Creative Writing | 1432 | 1438 |
| LMArena Multi-Turn | 1449 | 1456 |
| EQ-Bench Creative Writing | — | 1574 |
Frequently asked questions
Is GPT-6.1 Sol better than Grok 4.20 (Non-Reasoning)?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 48.6 on the Noometry Index. Grok 4.20 (Non-Reasoning) costs 2.6× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6.1 Sol or Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GPT-6.1 Sol lists at $2 and $10.
Is GPT-6.1 Sol or Grok 4.20 (Non-Reasoning) better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 42.1 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 1M.
How many benchmarks do GPT-6.1 Sol and Grok 4.20 (Non-Reasoning) share?
25 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.