Model comparison
GPT-4 vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 29.1 on the Noometry Index.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.20 (Non-Reasoning) leads 48.2 to 10.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 92.2% for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 per million input/output tokens, against $30 / $60 for GPT-4.
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 8K.
Side by side
| GPT-4 | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 29.1 | 48.6 |
| Released | 2023-03-14 | 2026-02-17 |
| Weights | Proprietary | Proprietary |
| Context window | 8K | 1M |
| Max output | 8K | 30K |
| Input $ / M tokens | $30 | $1.25 |
| Output $ / M tokens | $60 | $2.50 |
| Results tracked | 38 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
GPT-4: 31.6 (#283), Grok 4.20 (Non-Reasoning): 42.1 (#112)
| Benchmark | GPT-4 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| WeirdML | 12.4% | 52.3% |
| LMArena Coding | 1254 | 1459 |
| LMArena WebDev | — | 1375 |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| ALE-Bench | — | 1,150 |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, Grok 4.20 (Non-Reasoning): 34.4 (#46)
| Benchmark | GPT-4 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| METR Time Horizons | 36.1% | — |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
GPT-4: 17.8 (#289), Grok 4.20 (Non-Reasoning): 52.3 (#32)
| Benchmark | GPT-4 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Chess Puzzles | 4% | 24% |
| LMArena Hard Prompts | 1241 | 1451 |
| DTBench | 62.7% | 90.1% |
| LMCA | 17.1% | 38.7% |
| Epoch Capabilities Index | 125.89 | 151.98 |
| ForecastBench | 57.8 | 61.4 |
| ARC-AGI-2 | — | 65.1% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| Thematic Generalization | — | 63.8% |
| Mystery Game Puzzles | 12% | — |
| BIG-Bench Hard | 75.1% | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Grok 4.20 (Non-Reasoning) leads
GPT-4: 10.8 (#309), Grok 4.20 (Non-Reasoning): 48.2 (#65)
| Benchmark | GPT-4 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 92.2% |
| LMArena Math | 1269 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
GPT-4: 18.4 (#282), Grok 4.20 (Non-Reasoning): 52.8 (#60)
| Benchmark | GPT-4 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 35.7% | 89.3% |
| LMArena Expert | 1211 | 1439 |
| SimpleQA Verified | — | 30.2% |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multimodal Not comparable
GPT-4: —, Grok 4.20 (Non-Reasoning): 33.3 (#98)
| Benchmark | GPT-4 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Grok 4.20 (Non-Reasoning) leads
GPT-4: 40.6 (#215), Grok 4.20 (Non-Reasoning): 54.5 (#40)
| Benchmark | GPT-4 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1246 | 1441 |
| LMArena Chinese | 1242 | 1481 |
| LMArena French | 1283 | 1476 |
| LMArena German | 1251 | 1465 |
| LMArena Japanese | 1209 | 1449 |
| LMArena Korean | 1184 | 1417 |
| LMArena Russian | 1251 | 1458 |
| LMArena Spanish | 1261 | 1443 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
GPT-4: 65.3 (#222), Grok 4.20 (Non-Reasoning): 74.8 (#83)
| Benchmark | GPT-4 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1241 | 1420 |
Long Context Grok 4.20 (Non-Reasoning) leads
GPT-4: 37.7 (#212), Grok 4.20 (Non-Reasoning): 45.5 (#34)
| Benchmark | GPT-4 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1244 | 1437 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
GPT-4: 34.9 (#268), Grok 4.20 (Non-Reasoning): 65.7 (#44)
| Benchmark | GPT-4 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1263 | 1451 |
| LMArena Creative Writing | 1244 | 1438 |
| EQ-Bench Creative Writing | 752 | 1574 |
| LMArena Multi-Turn | 1257 | 1456 |
Frequently asked questions
Is GPT-4 better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 29.1 on the Noometry Index.
Which is cheaper, GPT-4 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-4 lists at $30 and $60.
Is GPT-4 or Grok 4.20 (Non-Reasoning) better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 31.6 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 (Non-Reasoning) does, with 1M tokens against 8K.
How many benchmarks do GPT-4 and Grok 4.20 (Non-Reasoning) share?
26 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.