Model comparison
Ministral 3B vs Qwen3 14B
Qwen3 14B is the stronger model overall, scoring 35.5 to 26.2 on the Noometry Index. Ministral 3B costs 6.1× less per token, which makes it the better buy when Qwen3 14B's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. Ministral 3B scores higher in 0 categories and Qwen3 14B in 3 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 14B leads 39.3 to 10.4.
- The biggest single-benchmark swing is GPQA Diamond: 25.3% for Ministral 3B and 63.8% for Qwen3 14B.
- Ministral 3B is cheaper at $0.10 / $0.10 per million input/output tokens, against $0.35 / $1.40 for Qwen3 14B.
Side by side
| Ministral 3B | Qwen3 14B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 26.2 | 35.5 |
| Released | 2024-10-01 | 2025-04 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 262K | 8K |
| Input $ / M tokens | $0.10 | $0.35 |
| Output $ / M tokens | $0.10 | $1.40 |
| Results tracked | 6 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Ministral 3B: —, Qwen3 14B: 37.3 (#195)
| Benchmark | Ministral 3B | Qwen3 14B |
|---|---|---|
| SciCode | — | 31.6% |
Agentic & Tool Use Not comparable
Ministral 3B: —, Qwen3 14B: 29.6 (#83)
| Benchmark | Ministral 3B | Qwen3 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41% |
Reasoning Too close to call
Ministral 3B: 18.4 (#282), Qwen3 14B: 18.5 (#280)
| Benchmark | Ministral 3B | Qwen3 14B |
|---|---|---|
| DTBench | 51.7% | 64% |
| LMCA | 5.5% | 18.2% |
| Epoch Capabilities Index | 118.1 | 138.23 |
| Kagi LLM Benchmark | — | 49.1% |
| CritPt | — | 0% |
| Chess Puzzles | — | 4% |
Math Qwen3 14B leads
Ministral 3B: 26.6 (#258), Qwen3 14B: 38.6 (#133)
| Benchmark | Ministral 3B | Qwen3 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.4% |
| MATH Level 5 | 14.4% | — |
Knowledge Qwen3 14B leads
Ministral 3B: 10.4 (#302), Qwen3 14B: 39.3 (#134)
| Benchmark | Ministral 3B | Qwen3 14B |
|---|---|---|
| GPQA Diamond | 25.3% | 63.8% |
| Vectara Hallucination Rate | 7.3% | 5.4% |
Long Context Not comparable
Ministral 3B: —, Qwen3 14B: 38.1 (#204)
| Benchmark | Ministral 3B | Qwen3 14B |
|---|---|---|
| Fiction.LiveBench | — | 62.5% |
Frequently asked questions
Is Ministral 3B better than Qwen3 14B?
Qwen3 14B is the stronger model overall, scoring 35.5 to 26.2 on the Noometry Index. Ministral 3B costs 6.1× less per token, which makes it the better buy when Qwen3 14B's lead doesn't matter for your workload.
Which is cheaper, Ministral 3B or Qwen3 14B?
Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Qwen3 14B lists at $0.35 and $1.40.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Ministral 3B and Qwen3 14B share?
5 benchmarks have published results for both models. Ministral 3B has 6 scored results on Noometry and Qwen3 14B has 12.