Model comparison
Mercury 2 vs Mistral 7B
Mercury 2 is the stronger model overall, scoring 39.1 to 23.0 on the Noometry Index. Mistral 7B costs 1.5× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.
Last verified . 11 shared benchmarks.
Mistral AISummary
- They share 11 benchmarks with published results for both. Mercury 2 scores higher in 7 categories and Mistral 7B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mercury 2 leads 36.2 to 7.4.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- Mercury 2 accepts more context: 128K tokens versus 8K.
- Mistral 7B has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Mistral 7B | |
|---|---|---|
| Provider | Inception | Mistral AI |
| Noometry Index | 39.1 | 23.0 |
| Released | 2026-02-20 | 2023-09-27 |
| Weights | Proprietary | Open |
| Context window | 128K | 8K |
| Max output | 50K | 8K |
| Input $ / M tokens | $0.25 | $0.25 |
| Output $ / M tokens | $0.75 | $0.25 |
| Results tracked | 17 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2 leads
Mercury 2: 33.5 (#255), Mistral 7B: 26.4 (#326)
| Benchmark | Mercury 2 | Mistral 7B |
|---|---|---|
| LMArena Coding | 1391 | 1082 |
| LMArena WebDev | 1171 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| ALE-Bench | 785.58 | — |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Reasoning Mercury 2 leads
Mercury 2: 23.8 (#170), Mistral 7B: 13.1 (#336)
| Benchmark | Mercury 2 | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1067 |
| CritPt | 0.8% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| Epoch Capabilities Index | — | 112.21 |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math Not comparable
Mercury 2: —, Mistral 7B: 8.1 (#325)
| Benchmark | Mercury 2 | Mistral 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| LMArena Math | — | 1085 |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |
Knowledge Mercury 2 leads
Mercury 2: 36.2 (#172), Mistral 7B: 7.4 (#311)
| Benchmark | Mercury 2 | Mistral 7B |
|---|---|---|
| LMArena Expert | 1358 | 1036 |
| GPQA Diamond | — | 15.2% |
| Vectara Hallucination Rate | 12.3% | — |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multilingual Mercury 2 leads
Mercury 2: 46.6 (#157), Mistral 7B: 25.8 (#283)
| Benchmark | Mercury 2 | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1331 | 1012 |
| LMArena Chinese | 1417 | 1009 |
| LMArena Russian | 1304 | 1018 |
| LMArena French | — | 1037 |
| LMArena German | — | 987 |
| LMArena Japanese | — | 878 |
| LMArena Spanish | — | 1026 |
Instruction Following Mercury 2 leads
Mercury 2: 70.2 (#165), Mistral 7B: 54.2 (#280)
| Benchmark | Mercury 2 | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1329 | 1060 |
Long Context Mercury 2 leads
Mercury 2: 40.5 (#154), Mistral 7B: 32.2 (#271)
| Benchmark | Mercury 2 | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1330 | 1060 |
Writing & Preference Mercury 2 leads
Mercury 2: 53.8 (#155), Mistral 7B: 30.7 (#286)
| Benchmark | Mercury 2 | Mistral 7B |
|---|---|---|
| LMArena Text | 1355 | 1090 |
| LMArena Creative Writing | 1289 | 1068 |
| LMArena Multi-Turn | 1358 | 1062 |
Frequently asked questions
Is Mercury 2 better than Mistral 7B?
Mercury 2 is the stronger model overall, scoring 39.1 to 23.0 on the Noometry Index. Mistral 7B costs 1.5× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.
Which is cheaper, Mercury 2 or Mistral 7B?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Mercury 2 lists at $0.25 and $0.75.
Is Mercury 2 or Mistral 7B better for coding?
Mercury 2 scores higher on coding benchmarks: 33.5 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
Mercury 2 does, with 128K tokens against 8K.
How many benchmarks do Mercury 2 and Mistral 7B share?
11 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Mistral 7B has 37.