Model comparison
Mercury 2 vs Ministral 8B
Mercury 2 is the stronger model overall, scoring 39.1 to 28.2 on the Noometry Index. Ministral 8B costs 2.5× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Mistral AISummary
- They share 12 benchmarks with published results for both. Mercury 2 scores higher in 6 categories and Ministral 8B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mercury 2 leads 36.2 to 12.6.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- Ministral 8B accepts more context: 262K tokens versus 128K.
- Ministral 8B has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Ministral 8B | |
|---|---|---|
| Provider | Inception | Mistral AI |
| Noometry Index | 39.1 | 28.2 |
| Released | 2026-02-20 | 2024-10-01 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 50K | 262K |
| Input $ / M tokens | $0.25 | $0.15 |
| Output $ / M tokens | $0.75 | $0.15 |
| Results tracked | 17 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Mercury 2: 33.5 (#255), Ministral 8B: 35.0 (#230)
| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Coding | 1391 | 1202 |
| LMArena WebDev | 1171 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |
Agentic & Tool Use Not comparable
Mercury 2: —, Ministral 8B: 16.4 (#148)
| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Mercury 2 leads
Mercury 2: 23.8 (#170), Ministral 8B: 18.4 (#281)
| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1191 |
| CritPt | 0.8% | — |
| DTBench | — | 45.7% |
Math Not comparable
Mercury 2: —, Ministral 8B: 25.7 (#267)
| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Math | — | 1188 |
| MATH Level 5 | — | 14.9% |
Knowledge Mercury 2 leads
Mercury 2: 36.2 (#172), Ministral 8B: 12.6 (#297)
| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | 7.4% |
| LMArena Expert | 1358 | 1170 |
| GPQA Diamond | — | 27.1% |
Multilingual Mercury 2 leads
Mercury 2: 46.6 (#157), Ministral 8B: 35.1 (#247)
| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1331 | 1165 |
| LMArena Chinese | 1417 | 1193 |
| LMArena Russian | 1304 | 1195 |
Instruction Following Mercury 2 leads
Mercury 2: 70.2 (#165), Ministral 8B: 60.5 (#250)
| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1329 | 1161 |
Long Context Mercury 2 leads
Mercury 2: 40.5 (#154), Ministral 8B: 36.7 (#227)
| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1330 | 1212 |
Writing & Preference Mercury 2 leads
Mercury 2: 53.8 (#155), Ministral 8B: 39.6 (#246)
| Benchmark | Mercury 2 | Ministral 8B |
|---|---|---|
| LMArena Text | 1355 | 1191 |
| LMArena Creative Writing | 1289 | 1175 |
| LMArena Multi-Turn | 1358 | 1166 |
Frequently asked questions
Is Mercury 2 better than Ministral 8B?
Mercury 2 is the stronger model overall, scoring 39.1 to 28.2 on the Noometry Index. Ministral 8B costs 2.5× 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 Ministral 8B?
Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Mercury 2 lists at $0.25 and $0.75.
Is Mercury 2 or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Ministral 8B does, with 262K tokens against 128K.
How many benchmarks do Mercury 2 and Ministral 8B share?
12 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Ministral 8B has 17.