Model comparison
GPT-4 Turbo vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 30.3 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.20 (Non-Reasoning) leads 48.0 to 8.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo 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 $10 / $30 for GPT-4 Turbo.
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 128K.
Side by side
| GPT-4 Turbo | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 30.3 | 48.5 |
| Released | 2023-11-06 | 2026-02-17 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 30K |
| Input $ / M tokens | $10 | $1.25 |
| Output $ / M tokens | $30 | $2.50 |
| Results tracked | 36 | 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 Turbo: 33.4 (#247), Grok 4.20 (Non-Reasoning): 41.8 (#104)
| Benchmark | GPT-4 Turbo | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| WeirdML | 18% | 52.3% |
| LMArena Coding | 1268 | 1458 |
| LMArena WebDev | — | 1374 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 58.2% | — |
| ALE-Bench | — | 1,150 |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Grok 4.20 (Non-Reasoning): 34.3 (#43)
| Benchmark | GPT-4 Turbo | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| METR Time Horizons | 36.7% | — |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
GPT-4 Turbo: 14.9 (#311), Grok 4.20 (Non-Reasoning): 52.2 (#30)
| Benchmark | GPT-4 Turbo | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Chess Puzzles | 6% | 24% |
| LMArena Hard Prompts | 1251 | 1451 |
| DTBench | 61.6% | 90.1% |
| LMCA | 9.8% | 38.7% |
| Epoch Capabilities Index | 127.25 | 152.01 |
| ForecastBench | 59.4 | 61.4 |
| ARC-AGI-2 | — | 65.1% |
| SimpleBench | 25.1% | — |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| Thematic Generalization | — | 63.8% |
Math Grok 4.20 (Non-Reasoning) leads
GPT-4 Turbo: 8.6 (#316), Grok 4.20 (Non-Reasoning): 48.0 (#54)
| Benchmark | GPT-4 Turbo | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 44.9% |
| OTIS Mock AIME 2024-2025 | 6.7% | 92.2% |
| LMArena Math | 1272 | 1455 |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
| MATH Level 5 | 46.7% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
GPT-4 Turbo: 24.3 (#263), Grok 4.20 (Non-Reasoning): 52.8 (#54)
| Benchmark | GPT-4 Turbo | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 46.6% | 89.3% |
| LMArena Expert | 1223 | 1440 |
| SimpleQA Verified | — | 30.2% |
| Confabulations | 28.4% | — |
| MMLU | 81.3% | — |
Multimodal Grok 4.20 (Non-Reasoning) leads
GPT-4 Turbo: 30.0 (#104), Grok 4.20 (Non-Reasoning): 33.2 (#88)
| Benchmark | GPT-4 Turbo | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1090 | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Grok 4.20 (Non-Reasoning) leads
GPT-4 Turbo: 40.7 (#211), Grok 4.20 (Non-Reasoning): 54.7 (#38)
| Benchmark | GPT-4 Turbo | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1245 | 1440 |
| LMArena Chinese | 1242 | 1481 |
| LMArena French | 1275 | 1477 |
| LMArena German | 1259 | 1463 |
| LMArena Japanese | 1194 | 1450 |
| LMArena Korean | 1187 | 1417 |
| LMArena Russian | 1259 | 1457 |
| LMArena Spanish | 1260 | 1442 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
GPT-4 Turbo: 66.0 (#211), Grok 4.20 (Non-Reasoning): 75.0 (#79)
| Benchmark | GPT-4 Turbo | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1250 | 1420 |
Long Context Grok 4.20 (Non-Reasoning) leads
GPT-4 Turbo: 38.0 (#200), Grok 4.20 (Non-Reasoning): 45.4 (#33)
| Benchmark | GPT-4 Turbo | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1254 | 1436 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
GPT-4 Turbo: 47.9 (#201), Grok 4.20 (Non-Reasoning): 65.9 (#42)
| Benchmark | GPT-4 Turbo | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1272 | 1451 |
| LMArena Creative Writing | 1269 | 1439 |
| LMArena Multi-Turn | 1267 | 1456 |
| EQ-Bench Creative Writing | — | 1574 |
Frequently asked questions
Is GPT-4 Turbo better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 30.3 on the Noometry Index.
Which is cheaper, GPT-4 Turbo 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 Turbo lists at $10 and $30.
Is GPT-4 Turbo or Grok 4.20 (Non-Reasoning) better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 33.4 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 GPT-4 Turbo and Grok 4.20 (Non-Reasoning) share?
27 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.