Model comparison
GPT-4 Turbo vs Llama 4 Maverick
GPT-4 Turbo and Llama 4 Maverick score almost the same on the Noometry Index (30.5 vs 30.9), so choose on price, context window or the category you care about most.
Last verified . 30 shared benchmarks.
MetaSummary
- They share 30 benchmarks with published results for both. GPT-4 Turbo scores higher in 4 categories and Llama 4 Maverick in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 4 Maverick leads 26.0 to 9.0.
- The biggest single-benchmark swing is MATH Level 5: 46.7% for GPT-4 Turbo and 73% for Llama 4 Maverick.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| GPT-4 Turbo | Llama 4 Maverick | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 30.5 | 30.9 |
| Released | 2023-11-06 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 128K | 128K |
| Max output | 4K | 4K |
| Input $ / M tokens | $10 | $0.19 |
| Output $ / M tokens | $30 | $0.65 |
| Results tracked | 36 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4 Turbo leads
GPT-4 Turbo: 33.8 (#249), Llama 4 Maverick: 26.6 (#324)
| Benchmark | GPT-4 Turbo | Llama 4 Maverick |
|---|---|---|
| WeirdML | 18% | 24.5% |
| BigCodeBench Instruct | 48.2% | 49.7% |
| LMArena Coding | 1268 | 1302 |
| BigCodeBench Complete | 58.2% | 61.4% |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| SciCode | — | 33.1% |
| ALE-Bench | — | 172.97 |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Llama 4 Maverick: 28.2 (#91)
| Benchmark | GPT-4 Turbo | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
| METR Time Horizons | 36.7% | — |
Reasoning GPT-4 Turbo leads
GPT-4 Turbo: 15.3 (#317), Llama 4 Maverick: 10.1 (#342)
| Benchmark | GPT-4 Turbo | Llama 4 Maverick |
|---|---|---|
| SimpleBench | 25.1% | 27.7% |
| LMArena Hard Prompts | 1251 | 1281 |
| DTBench | 61.6% | 61.9% |
| LMCA | 9.8% | 15.9% |
| Epoch Capabilities Index | 127.25 | 132.2 |
| ForecastBench | 59.4 | 57.5 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| CritPt | — | 0% |
| Chess Puzzles | 6% | — |
| EnigmaEval | — | 0.6% |
Math Llama 4 Maverick leads
GPT-4 Turbo: 9.0 (#322), Llama 4 Maverick: 26.0 (#262)
| Benchmark | GPT-4 Turbo | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 20.6% |
| LMArena Math | 1272 | 1299 |
| MATH Level 5 | 46.7% | 73% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| Omni-MATH | — | 42.2% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Llama 4 Maverick leads
GPT-4 Turbo: 24.3 (#268), Llama 4 Maverick: 33.4 (#204)
| Benchmark | GPT-4 Turbo | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 46.6% | 67% |
| Confabulations | 28.4% | 22.6% |
| LMArena Expert | 1223 | 1259 |
| Humanity's Last Exam | — | 5.7% |
| MMLU-Pro | — | 81% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |
| MMLU | 81.3% | — |
Multimodal Too close to call
GPT-4 Turbo: 30.6 (#110), Llama 4 Maverick: 31.6 (#105)
| Benchmark | GPT-4 Turbo | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 1090 | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual Llama 4 Maverick leads
GPT-4 Turbo: 40.5 (#216), Llama 4 Maverick: 42.2 (#195)
| Benchmark | GPT-4 Turbo | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1245 | 1269 |
| LMArena Chinese | 1242 | 1277 |
| LMArena French | 1276 | 1259 |
| LMArena German | 1259 | 1291 |
| LMArena Japanese | 1194 | 1207 |
| LMArena Korean | 1187 | 1203 |
| LMArena Russian | 1259 | 1286 |
| LMArena Spanish | 1260 | 1293 |
Instruction Following Llama 4 Maverick leads
GPT-4 Turbo: 65.8 (#216), Llama 4 Maverick: 71.7 (#146)
| Benchmark | GPT-4 Turbo | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1249 | 1267 |
| IFEval | — | 90.8% |
Long Context GPT-4 Turbo leads
GPT-4 Turbo: 38.0 (#206), Llama 4 Maverick: 31.4 (#279)
| Benchmark | GPT-4 Turbo | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1254 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference GPT-4 Turbo leads
GPT-4 Turbo: 47.7 (#206), Llama 4 Maverick: 38.8 (#252)
| Benchmark | GPT-4 Turbo | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1272 | 1287 |
| LMArena Creative Writing | 1269 | 1267 |
| LMArena Multi-Turn | 1267 | 1289 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
| WildBench | — | 80% |
Frequently asked questions
Is GPT-4 Turbo better than Llama 4 Maverick?
GPT-4 Turbo and Llama 4 Maverick score almost the same on the Noometry Index (30.5 vs 30.9), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-4 Turbo or Llama 4 Maverick?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is GPT-4 Turbo or Llama 4 Maverick better for coding?
GPT-4 Turbo scores higher on coding benchmarks: 33.8 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do GPT-4 Turbo and Llama 4 Maverick share?
30 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Llama 4 Maverick has 54.