Model comparison
Llama-3.3-70B-Instruct vs Palm 2
Llama-3.3-70B-Instruct and Palm 2 score almost the same on the Noometry Index (30.6 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 10 shared benchmarks.
Meta
GoogleSummary
- They share 10 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 4 categories and Palm 2 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama-3.3-70B-Instruct leads 47.6 to 25.6.
- Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.
Side by side
| Llama-3.3-70B-Instruct | Palm 2 | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.6 | 30.0 |
| Released | 2024-12-06 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.32 | — |
| Results tracked | 43 | 10 |
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), Palm 2: 29.0 (#311)
| Benchmark | Llama-3.3-70B-Instruct | Palm 2 |
|---|---|---|
| LMArena Coding | 1268 | 994 |
| 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), Palm 2: —
| Benchmark | Llama-3.3-70B-Instruct | Palm 2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | — |
| BALROG | 23% | — |
Reasoning Palm 2 leads
Llama-3.3-70B-Instruct: 14.1 (#327), Palm 2: 19.1 (#271)
| Benchmark | Llama-3.3-70B-Instruct | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1005 |
| 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 Palm 2 leads
Llama-3.3-70B-Instruct: 15.3 (#298), Palm 2: 30.8 (#231)
| Benchmark | Llama-3.3-70B-Instruct | Palm 2 |
|---|---|---|
| LMArena Math | 1267 | 1049 |
| 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), Palm 2: —
| Benchmark | Llama-3.3-70B-Instruct | Palm 2 |
|---|---|---|
| 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), Palm 2: 20.9 (#295)
| Benchmark | Llama-3.3-70B-Instruct | Palm 2 |
|---|---|---|
| LMArena Non-English | 1236 | 916 |
| LMArena Chinese | 1217 | 887 |
| 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), Palm 2: 51.0 (#296)
| Benchmark | Llama-3.3-70B-Instruct | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1242 | 1010 |
| LiveBench Instruction Following | 82.7% | — |
Long Context Palm 2 leads
Llama-3.3-70B-Instruct: 26.4 (#295), Palm 2: 30.8 (#285)
| Benchmark | Llama-3.3-70B-Instruct | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1256 | 1010 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 47.6 (#207), Palm 2: 25.6 (#304)
| Benchmark | Llama-3.3-70B-Instruct | Palm 2 |
|---|---|---|
| LMArena Text | 1274 | 1027 |
| LMArena Creative Writing | 1250 | 991 |
| LMArena Multi-Turn | 1280 | 994 |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than Palm 2?
Llama-3.3-70B-Instruct and Palm 2 score almost the same on the Noometry Index (30.6 vs 30.0), so choose on price, context window or the category you care about most.
Is Llama-3.3-70B-Instruct or Palm 2 better for coding?
Llama-3.3-70B-Instruct scores higher on coding benchmarks: 31.0 versus 29.0 in the Noometry coding category.
How many benchmarks do Llama-3.3-70B-Instruct and Palm 2 share?
10 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Palm 2 has 10.