Model comparison
Llama-3.3-70B-Instruct vs Llama2 70b Steerlm Chat
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 30.6 on the Noometry Index.
Last verified . 9 shared benchmarks.
Meta
NVIDIASummary
- They share 9 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 4 categories and Llama2 70b Steerlm Chat in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama-3.3-70B-Instruct leads 71.1 to 54.2.
Side by side
| Llama-3.3-70B-Instruct | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 30.6 | 31.8 |
| Released | 2024-12-06 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.32 | — |
| Results tracked | 43 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 31.0 (#290), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | Llama-3.3-70B-Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1268 | 1025 |
| SciCode | 26% | — |
| WeirdML | 14.4% | — |
| BigCodeBench Instruct | 46.9% | — |
| LiveBench Coding | 36.6% | — |
| BigCodeBench Complete | 57.5% | — |
Agentic & Tool Use Not comparable
Llama-3.3-70B-Instruct: 25.8 (#105), Llama2 70b Steerlm Chat: —
| Benchmark | Llama-3.3-70B-Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | — |
| BALROG | 23% | — |
Reasoning Llama2 70b Steerlm Chat leads
Llama-3.3-70B-Instruct: 14.1 (#327), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | Llama-3.3-70B-Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1047 |
| SimpleBench | 19.9% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 50.8% | — |
| DTBench | 59.5% | — |
| LiveBench Data Analysis | 49.5% | — |
| LMCA | 17.5% | — |
| Epoch Capabilities Index | 127.33 | — |
| ForecastBench | 58.6 | — |
| LiveBench | 50.2% | — |
Math Llama2 70b Steerlm Chat leads
Llama-3.3-70B-Instruct: 15.3 (#298), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | Llama-3.3-70B-Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1267 | 1072 |
| OTIS Mock AIME 2024-2025 | 5.1% | — |
| LiveBench Math | 42.2% | — |
| MATH Level 5 | 41.6% | — |
Knowledge Not comparable
Llama-3.3-70B-Instruct: 30.6 (#226), Llama2 70b Steerlm Chat: —
| Benchmark | Llama-3.3-70B-Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| GPQA Diamond | 47.4% | — |
| Confabulations | 22.8% | — |
| Vectara Hallucination Rate | 4.1% | — |
| LMArena Expert | 1225 | — |
| MMLU | 86.3% | — |
Multilingual Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 39.9 (#220), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | Llama-3.3-70B-Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1236 | 1063 |
| LMArena Chinese | 1217 | — |
| LMArena French | 1281 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1150 | — |
| LMArena Korean | 1143 | — |
| LMArena Russian | 1252 | — |
| LMArena Spanish | 1270 | — |
Instruction Following Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 71.1 (#157), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | Llama-3.3-70B-Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1242 | 1060 |
| LiveBench Instruction Following | 82.7% | — |
Long Context Llama2 70b Steerlm Chat leads
Llama-3.3-70B-Instruct: 26.4 (#295), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | Llama-3.3-70B-Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1256 | 998 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 47.6 (#207), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | Llama-3.3-70B-Instruct | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1274 | 1098 |
| LMArena Creative Writing | 1250 | 1091 |
| LMArena Multi-Turn | 1280 | 1058 |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than Llama2 70b Steerlm Chat?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 30.6 on the Noometry Index.
Is Llama-3.3-70B-Instruct or Llama2 70b Steerlm Chat better for coding?
Llama-3.3-70B-Instruct scores higher on coding benchmarks: 31.0 versus 29.9 in the Noometry coding category.
How many benchmarks do Llama-3.3-70B-Instruct and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Llama2 70b Steerlm Chat has 9.