Model comparison
Mixtral 8x22B vs Palm 2
Palm 2 is the stronger model overall, scoring 29.4 to 26.7 on the Noometry Index.
Last verified . 10 shared benchmarks.
Mistral AI
GoogleSummary
- They share 10 benchmarks with published results for both. Mixtral 8x22B scores higher in 5 categories and Palm 2 in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mixtral 8x22B leads 32.9 to 21.1.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| Mixtral 8x22B | Palm 2 | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 26.7 | 29.4 |
| Released | 2024-04-17 | — |
| Weights | Open | Proprietary |
| Context window | 64K | — |
| Max output | 64K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 34 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Palm 2 leads
Mixtral 8x22B: 23.8 (#324), Palm 2: 28.5 (#306)
| Benchmark | Mixtral 8x22B | Palm 2 |
|---|---|---|
| LMArena Coding | 1166 | 995 |
| WeirdML | 3.2% | — |
| BigCodeBench Instruct | 40.6% | — |
| BigCodeBench Complete | 50.2% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |
Agentic & Tool Use Not comparable
Mixtral 8x22B: 22.8 (#119), Palm 2: —
| Benchmark | Mixtral 8x22B | Palm 2 |
|---|---|---|
| Cybench | 7.5% | — |
Reasoning Too close to call
Mixtral 8x22B: 19.1 (#246), Palm 2: 18.2 (#270)
| Benchmark | Mixtral 8x22B | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1005 |
| DTBench | 55.1% | — |
| Epoch Capabilities Index | 122 | — |
| ForecastBench | 56.3 | — |
Math Palm 2 leads
Mixtral 8x22B: 21.2 (#271), Palm 2: 28.4 (#229)
| Benchmark | Mixtral 8x22B | Palm 2 |
|---|---|---|
| LMArena Math | 1184 | 1049 |
| Omni-MATH | 16.3% | — |
| MATH Level 5 | 24.2% | — |
Knowledge Not comparable
Mixtral 8x22B: 15.1 (#288), Palm 2: —
| Benchmark | Mixtral 8x22B | Palm 2 |
|---|---|---|
| GPQA Diamond | 34.1% | — |
| MMLU-Pro | 46% | — |
| GPQA (HELM) | 33.4% | — |
| LMArena Expert | 1113 | — |
| MMLU | 77.8% | — |
Multilingual Mixtral 8x22B leads
Mixtral 8x22B: 32.9 (#250), Palm 2: 21.1 (#290)
| Benchmark | Mixtral 8x22B | Palm 2 |
|---|---|---|
| LMArena Non-English | 1128 | 916 |
| LMArena Chinese | 1116 | 887 |
| LMArena French | 1165 | — |
| LMArena German | 1141 | — |
| LMArena Japanese | 1037 | — |
| LMArena Korean | 1056 | — |
| LMArena Russian | 1158 | — |
| LMArena Spanish | 1150 | — |
Instruction Following Mixtral 8x22B leads
Mixtral 8x22B: 57.9 (#261), Palm 2: 51.3 (#291)
| Benchmark | Mixtral 8x22B | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1147 | 1010 |
| IFEval | 72.4% | — |
Long Context Mixtral 8x22B leads
Mixtral 8x22B: 34.6 (#242), Palm 2: 30.7 (#280)
| Benchmark | Mixtral 8x22B | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1144 | 1010 |
Writing & Preference Mixtral 8x22B leads
Mixtral 8x22B: 37.1 (#257), Palm 2: 25.7 (#299)
| Benchmark | Mixtral 8x22B | Palm 2 |
|---|---|---|
| LMArena Text | 1162 | 1027 |
| LMArena Creative Writing | 1141 | 991 |
| LMArena Multi-Turn | 1130 | 994 |
| WildBench | 71.1% | — |
Frequently asked questions
Is Mixtral 8x22B better than Palm 2?
Palm 2 is the stronger model overall, scoring 29.4 to 26.7 on the Noometry Index.
Is Mixtral 8x22B or Palm 2 better for coding?
Palm 2 scores higher on coding benchmarks: 28.5 versus 23.8 in the Noometry coding category.
How many benchmarks do Mixtral 8x22B and Palm 2 share?
10 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Palm 2 has 10.