Model comparison
Llama 4 Maverick vs Llama2 70b Steerlm Chat
Llama 4 Maverick and Llama2 70b Steerlm Chat score almost the same on the Noometry Index (30.9 vs 31.8), so choose on price, context window or the category you care about most.
Last verified . 9 shared benchmarks.
Meta
NVIDIASummary
- They share 9 benchmarks with published results for both. Llama 4 Maverick scores higher in 4 categories and Llama2 70b Steerlm Chat in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 4 Maverick leads 71.7 to 54.2.
Side by side
| Llama 4 Maverick | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 30.9 | 31.8 |
| Released | 2025-04-05 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.19 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 54 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama2 70b Steerlm Chat leads
Llama 4 Maverick: 26.6 (#324), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | Llama 4 Maverick | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1302 | 1025 |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| SciCode | 33.1% | — |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| BigCodeBench Complete | 61.4% | — |
| ALE-Bench | 172.97 | — |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 28.2 (#91), Llama2 70b Steerlm Chat: —
| Benchmark | Llama 4 Maverick | Llama2 70b Steerlm Chat |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Llama2 70b Steerlm Chat leads
Llama 4 Maverick: 10.1 (#342), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | Llama 4 Maverick | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1281 | 1047 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| CritPt | 0% | — |
| EnigmaEval | 0.6% | — |
| DTBench | 61.9% | — |
| LMCA | 15.9% | — |
| Epoch Capabilities Index | 132.2 | — |
| ForecastBench | 57.5 | — |
Math Llama2 70b Steerlm Chat leads
Llama 4 Maverick: 26.0 (#262), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | Llama 4 Maverick | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1299 | 1072 |
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| Omni-MATH | 42.2% | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Not comparable
Llama 4 Maverick: 33.4 (#204), Llama2 70b Steerlm Chat: —
| Benchmark | Llama 4 Maverick | Llama2 70b Steerlm Chat |
|---|---|---|
| GPQA Diamond | 67% | — |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
| LMArena Expert | 1259 | — |
Multimodal Not comparable
Llama 4 Maverick: 31.6 (#105), Llama2 70b Steerlm Chat: —
| Benchmark | Llama 4 Maverick | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Vision | 1142 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Llama 4 Maverick leads
Llama 4 Maverick: 42.2 (#195), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | Llama 4 Maverick | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1269 | 1063 |
| LMArena Chinese | 1277 | — |
| LMArena French | 1259 | — |
| LMArena German | 1291 | — |
| LMArena Japanese | 1207 | — |
| LMArena Korean | 1203 | — |
| LMArena Russian | 1286 | — |
| LMArena Spanish | 1293 | — |
Instruction Following Llama 4 Maverick leads
Llama 4 Maverick: 71.7 (#146), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | Llama 4 Maverick | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1267 | 1060 |
| IFEval | 90.8% | — |
Long Context Too close to call
Llama 4 Maverick: 31.4 (#279), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | Llama 4 Maverick | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1280 | 998 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Llama 4 Maverick leads
Llama 4 Maverick: 38.8 (#252), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | Llama 4 Maverick | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1287 | 1098 |
| LMArena Creative Writing | 1267 | 1091 |
| LMArena Multi-Turn | 1289 | 1058 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than Llama2 70b Steerlm Chat?
Llama 4 Maverick and Llama2 70b Steerlm Chat score almost the same on the Noometry Index (30.9 vs 31.8), so choose on price, context window or the category you care about most.
Is Llama 4 Maverick or Llama2 70b Steerlm Chat better for coding?
Llama2 70b Steerlm Chat scores higher on coding benchmarks: 29.9 versus 26.6 in the Noometry coding category.
How many benchmarks do Llama 4 Maverick and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Llama2 70b Steerlm Chat has 9.