Model comparison
Falcon-180B vs Mistral 7B
Falcon-180B is the stronger model overall, scoring 32.2 to 23.0 on the Noometry Index.
Last verified . 15 shared benchmarks.
Technology Innovation Institute
Mistral AISummary
- They share 15 benchmarks with published results for both. Falcon-180B scores higher in 1 category and Mistral 7B in 3 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Falcon-180B leads 19.1 to 13.1.
Side by side
| Falcon-180B | Mistral 7B | |
|---|---|---|
| Provider | Technology Innovation Institute | Mistral AI |
| Noometry Index | 32.2 | 23.0 |
| Released | 2023-09-06 | 2023-09-27 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.25 |
| Results tracked | 16 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Mistral 7B: 26.4 (#326)
| Benchmark | Falcon-180B | Mistral 7B |
|---|---|---|
| BigCodeBench Instruct | — | 19.5% |
| LMArena Coding | — | 1082 |
| BigCodeBench Complete | — | 27.3% |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Reasoning Falcon-180B leads
Falcon-180B: 19.1 (#269), Mistral 7B: 13.1 (#336)
| Benchmark | Falcon-180B | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1067 |
| Epoch Capabilities Index | 112.13 | 112.21 |
| HellaSwag | 89% | 81% |
| PIQA | 84.9% | 83% |
| WinoGrande | 87.1% | 75.3% |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| LAMBADA | 79.8% | — |
Math Not comparable
Falcon-180B: —, Mistral 7B: 8.1 (#325)
| Benchmark | Falcon-180B | Mistral 7B |
|---|---|---|
| GSM8K | 54.4% | 54.4% |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| LMArena Math | — | 1085 |
| MATH Level 5 | — | 3.7% |
Knowledge Not comparable
Falcon-180B: —, Mistral 7B: 7.4 (#311)
| Benchmark | Falcon-180B | Mistral 7B |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 78.6% |
| BoolQ | 89% | 87.4% |
| MMLU | 70.6% | 62.5% |
| OpenBookQA | 64.2% | 79.8% |
| GPQA Diamond | — | 15.2% |
| LMArena Expert | — | 1036 |
| TriviaQA | — | 75.2% |
Multilingual Too close to call
Falcon-180B: 25.2 (#286), Mistral 7B: 25.8 (#283)
| Benchmark | Falcon-180B | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1000 | 1012 |
| LMArena Chinese | — | 1009 |
| LMArena French | — | 1037 |
| LMArena German | — | 987 |
| LMArena Japanese | — | 878 |
| LMArena Russian | — | 1018 |
| LMArena Spanish | — | 1026 |
Instruction Following Too close to call
Falcon-180B: 53.4 (#286), Mistral 7B: 54.2 (#280)
| Benchmark | Falcon-180B | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1047 | 1060 |
Long Context Not comparable
Falcon-180B: —, Mistral 7B: 32.2 (#271)
| Benchmark | Falcon-180B | Mistral 7B |
|---|---|---|
| LMArena Longer Query | — | 1060 |
Writing & Preference Mistral 7B leads
Falcon-180B: 29.1 (#295), Mistral 7B: 30.7 (#286)
| Benchmark | Falcon-180B | Mistral 7B |
|---|---|---|
| LMArena Text | 1054 | 1090 |
| LMArena Creative Writing | 1089 | 1068 |
| LMArena Multi-Turn | 1013 | 1062 |
Frequently asked questions
Is Falcon-180B better than Mistral 7B?
Falcon-180B is the stronger model overall, scoring 32.2 to 23.0 on the Noometry Index.
How many benchmarks do Falcon-180B and Mistral 7B share?
15 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Mistral 7B has 37.