Model comparison
GPT-3.5-turbo vs Palm 2
Palm 2 is the stronger model overall, scoring 29.4 to 23.1 on the Noometry Index.
Last verified . 10 shared benchmarks.
GoogleSummary
- They share 10 benchmarks with published results for both. GPT-3.5-turbo scores higher in 3 categories and Palm 2 in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Palm 2 leads 28.4 to 6.0.
Side by side
| GPT-3.5-turbo | Palm 2 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 23.1 | 29.4 |
| Released | 2023-03-01 | — |
| Weights | Proprietary | Proprietary |
| Context window | 16K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 44 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Palm 2 leads
GPT-3.5-turbo: 23.5 (#326), Palm 2: 28.5 (#306)
| Benchmark | GPT-3.5-turbo | Palm 2 |
|---|---|---|
| LMArena Coding | 1137 | 995 |
| WeirdML | 3.5% | — |
| BigCodeBench Instruct | 39.1% | — |
| BigCodeBench Complete | 50.6% | — |
| HumanEval+ | 70.7% | — |
| MBPP+ | 69.7% | — |
Agentic & Tool Use Not comparable
GPT-3.5-turbo: —, Palm 2: —
| Benchmark | GPT-3.5-turbo | Palm 2 |
|---|---|---|
| METR Time Horizons | 21.5% | — |
Reasoning Palm 2 leads
GPT-3.5-turbo: 13.3 (#328), Palm 2: 18.2 (#270)
| Benchmark | GPT-3.5-turbo | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1108 | 1005 |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 3% | — |
| DTBench | 48.5% | — |
| LMCA | 9.7% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 61.6% | — |
| CommonsenseQA 2.0 | 57% | — |
| Epoch Capabilities Index | 118.48 | — |
| ForecastBench | 50.4 | — |
| WinoGrande | 81.6% | — |
Math Palm 2 leads
GPT-3.5-turbo: 6.0 (#321), Palm 2: 28.4 (#229)
| Benchmark | GPT-3.5-turbo | Palm 2 |
|---|---|---|
| LMArena Math | 1142 | 1049 |
| FrontierMath (Tiers 1-3) | 0% | — |
| OTIS Mock AIME 2024-2025 | 2.2% | — |
| MATH Level 5 | 15.9% | — |
| GSM8K | 57.8% | — |
Knowledge Not comparable
GPT-3.5-turbo: 10.0 (#298), Palm 2: —
| Benchmark | GPT-3.5-turbo | Palm 2 |
|---|---|---|
| GPQA Diamond | 28% | — |
| LMArena Expert | 1070 | — |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| MMLU | 71.4% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |
Multilingual GPT-3.5-turbo leads
GPT-3.5-turbo: 31.6 (#253), Palm 2: 21.1 (#290)
| Benchmark | GPT-3.5-turbo | Palm 2 |
|---|---|---|
| LMArena Non-English | 1108 | 916 |
| LMArena Chinese | 1075 | 887 |
| LMArena French | 1117 | — |
| LMArena German | 1090 | — |
| LMArena Japanese | 1043 | — |
| LMArena Korean | 1019 | — |
| LMArena Russian | 1123 | — |
| LMArena Spanish | 1120 | — |
Instruction Following GPT-3.5-turbo leads
GPT-3.5-turbo: 58.1 (#257), Palm 2: 51.3 (#291)
| Benchmark | GPT-3.5-turbo | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1119 | 1010 |
Long Context GPT-3.5-turbo leads
GPT-3.5-turbo: 34.0 (#249), Palm 2: 30.7 (#280)
| Benchmark | GPT-3.5-turbo | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1121 | 1010 |
Writing & Preference Too close to call
GPT-3.5-turbo: 25.4 (#300), Palm 2: 25.7 (#299)
| Benchmark | GPT-3.5-turbo | Palm 2 |
|---|---|---|
| LMArena Text | 1125 | 1027 |
| LMArena Creative Writing | 1092 | 991 |
| LMArena Multi-Turn | 1117 | 994 |
| EQ-Bench Creative Writing | 451 | — |
Frequently asked questions
Is GPT-3.5-turbo better than Palm 2?
Palm 2 is the stronger model overall, scoring 29.4 to 23.1 on the Noometry Index.
Is GPT-3.5-turbo or Palm 2 better for coding?
Palm 2 scores higher on coding benchmarks: 28.5 versus 23.5 in the Noometry coding category.
How many benchmarks do GPT-3.5-turbo and Palm 2 share?
10 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Palm 2 has 10.