Model comparison
Falcon-40B vs Mixtral 8x7B
Mixtral 8x7B has enough public results to be ranked (#328); Falcon-40B does not yet, so treat this comparison as directional.
Last verified . 9 shared benchmarks.
Technology Innovation Institute
Mistral AISummary
- They share 9 benchmarks with published results for both.
Side by side
| Falcon-40B | Mixtral 8x7B | |
|---|---|---|
| Provider | Technology Innovation Institute | Mistral AI |
| Noometry Index | — | 26.8 |
| Released | 2023-03-15 | 2023-12-11 |
| Weights | Open | Open |
| Context window | — | 32K |
| Max output | — | 32K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 12 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-40B: —, Mixtral 8x7B: 32.2 (#265)
| Benchmark | Falcon-40B | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | — | 1127 |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Reasoning Not comparable
Falcon-40B: —, Mixtral 8x7B: 17.4 (#283)
| Benchmark | Falcon-40B | Mixtral 8x7B |
|---|---|---|
| Epoch Capabilities Index | 104.04 | 118.38 |
| HellaSwag | 85.3% | 86.7% |
| PIQA | 83% | 83.6% |
| WinoGrande | 76.9% | 77.2% |
| LMArena Hard Prompts | — | 1115 |
| DTBench | — | 49.6% |
| Adversarial NLI | — | 55.2% |
| BIG-Bench Hard | 37.1% | — |
| ForecastBench | — | 56.3 |
| LAMBADA | 77.3% | — |
Math Not comparable
Falcon-40B: —, Mixtral 8x7B: 17.2 (#284)
| Benchmark | Falcon-40B | Mixtral 8x7B |
|---|---|---|
| GSM8K | 33.8% | 74.4% |
| Omni-MATH | — | 10.5% |
| LMArena Math | — | 1147 |
| MATH Level 5 | — | 10% |
Knowledge Not comparable
Falcon-40B: —, Mixtral 8x7B: 11.0 (#296)
| Benchmark | Falcon-40B | Mixtral 8x7B |
|---|---|---|
| ARC (AI2) Challenge | 61.9% | 87.3% |
| MMLU | 56.9% | 70.6% |
| OpenBookQA | 56.6% | 85.8% |
| TriviaQA | 79.9% | 82.2% |
| GPQA Diamond | — | 30.6% |
| MMLU-Pro | — | 33.5% |
| GPQA (HELM) | — | 29.6% |
| LMArena Expert | — | 1088 |
| BoolQ | 83.1% | — |
Multilingual Not comparable
Falcon-40B: —, Mixtral 8x7B: 29.8 (#261)
| Benchmark | Falcon-40B | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | — | 1077 |
| LMArena Chinese | — | 1055 |
| LMArena French | — | 1165 |
| LMArena German | — | 1114 |
| LMArena Japanese | — | 931 |
| LMArena Korean | — | 968 |
| LMArena Russian | — | 1090 |
| LMArena Spanish | — | 1110 |
Instruction Following Not comparable
Falcon-40B: —, Mixtral 8x7B: 51.2 (#292)
| Benchmark | Falcon-40B | Mixtral 8x7B |
|---|---|---|
| IFEval | — | 57.5% |
| LMArena Instruction Following | — | 1110 |
Long Context Not comparable
Falcon-40B: —, Mixtral 8x7B: 33.4 (#255)
| Benchmark | Falcon-40B | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | — | 1103 |
Writing & Preference Not comparable
Falcon-40B: —, Mixtral 8x7B: 34.4 (#265)
| Benchmark | Falcon-40B | Mixtral 8x7B |
|---|---|---|
| LMArena Text | — | 1132 |
| LMArena Creative Writing | — | 1109 |
| WildBench | — | 67.3% |
| LMArena Multi-Turn | — | 1115 |
Frequently asked questions
Is Falcon-40B better than Mixtral 8x7B?
Mixtral 8x7B has enough public results to be ranked (#328); Falcon-40B does not yet, so treat this comparison as directional.
How many benchmarks do Falcon-40B and Mixtral 8x7B share?
9 benchmarks have published results for both models. Falcon-40B has 12 scored results on Noometry and Mixtral 8x7B has 38.