Model comparison
Mixtral 8x7B vs Olmo 2 0325 32b Instruct
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.7 to 27.1 on the Noometry Index.
Last verified . 16 shared benchmarks.
Mistral AI
Allen Institute for AI (Ai2)Summary
- They share 16 benchmarks with published results for both. Mixtral 8x7B scores higher in 0 categories and Olmo 2 0325 32b Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Olmo 2 0325 32b Instruct leads 61.5 to 51.0.
- The biggest single-benchmark swing is IFEval: 57.5% for Mixtral 8x7B and 78% for Olmo 2 0325 32b Instruct.
Side by side
| Mixtral 8x7B | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | Mistral AI | Allen Institute for AI (Ai2) |
| Noometry Index | 27.1 | 32.7 |
| Released | 2023-12-11 | — |
| Weights | Open | Open |
| Context window | 32K | — |
| Max output | 32K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 38 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 2 0325 32b Instruct leads
Mixtral 8x7B: 32.8 (#269), Olmo 2 0325 32b Instruct: 35.2 (#227)
| Benchmark | Mixtral 8x7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1126 | 1210 |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |
Reasoning Olmo 2 0325 32b Instruct leads
Mixtral 8x7B: 18.2 (#285), Olmo 2 0325 32b Instruct: 23.6 (#175)
| Benchmark | Mixtral 8x7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1208 |
| DTBench | 49.6% | — |
| Adversarial NLI | 55.2% | — |
| Epoch Capabilities Index | 118.47 | — |
| ForecastBench | 56.3 | — |
| HellaSwag | 86.7% | — |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |
Math Olmo 2 0325 32b Instruct leads
Mixtral 8x7B: 18.8 (#289), Olmo 2 0325 32b Instruct: 26.8 (#255)
| Benchmark | Mixtral 8x7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| Omni-MATH | 10.5% | 16.1% |
| LMArena Math | 1147 | 1208 |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |
Knowledge Olmo 2 0325 32b Instruct leads
Mixtral 8x7B: 11.0 (#301), Olmo 2 0325 32b Instruct: 19.5 (#279)
| Benchmark | Mixtral 8x7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| MMLU-Pro | 33.5% | 41.4% |
| GPQA (HELM) | 29.6% | 28.7% |
| GPQA Diamond | 30.6% | — |
| LMArena Expert | 1088 | — |
| ARC (AI2) Challenge | 87.3% | — |
| MMLU | 70.6% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |
Multilingual Olmo 2 0325 32b Instruct leads
Mixtral 8x7B: 29.6 (#266), Olmo 2 0325 32b Instruct: 34.8 (#248)
| Benchmark | Mixtral 8x7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1077 | 1160 |
| LMArena Chinese | 1055 | 1192 |
| LMArena Russian | 1090 | 1187 |
| LMArena French | 1166 | — |
| LMArena German | 1114 | — |
| LMArena Japanese | 931 | — |
| LMArena Korean | 968 | — |
| LMArena Spanish | 1111 | — |
Instruction Following Olmo 2 0325 32b Instruct leads
Mixtral 8x7B: 51.0 (#297), Olmo 2 0325 32b Instruct: 61.5 (#244)
| Benchmark | Mixtral 8x7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| IFEval | 57.5% | 78% |
| LMArena Instruction Following | 1109 | 1186 |
Long Context Olmo 2 0325 32b Instruct leads
Mixtral 8x7B: 33.4 (#260), Olmo 2 0325 32b Instruct: 36.2 (#234)
| Benchmark | Mixtral 8x7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1103 | 1194 |
Writing & Preference Olmo 2 0325 32b Instruct leads
Mixtral 8x7B: 34.2 (#270), Olmo 2 0325 32b Instruct: 42.1 (#236)
| Benchmark | Mixtral 8x7B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1132 | 1218 |
| LMArena Creative Writing | 1109 | 1199 |
| WildBench | 67.3% | 73.4% |
| LMArena Multi-Turn | 1115 | 1221 |
Frequently asked questions
Is Mixtral 8x7B better than Olmo 2 0325 32b Instruct?
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.7 to 27.1 on the Noometry Index.
Is Mixtral 8x7B or Olmo 2 0325 32b Instruct better for coding?
Olmo 2 0325 32b Instruct scores higher on coding benchmarks: 35.2 versus 32.8 in the Noometry coding category.
How many benchmarks do Mixtral 8x7B and Olmo 2 0325 32b Instruct share?
16 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.