Across 5 comparable benchmarks, Mistral Large 3 has better reported results on 3 and worse on 1, with 1 tied.
Moderate evidence5 of 5 shared results countedHow we compare
Price basis: Standard rates. The price section below shows the applicable periods.
| Fact | Ministral 3 14B | Mistral Large 3 |
|---|---|---|
| Context window | 256K tokens | 256K tokens |
| Input / 1M | $0.200 | $0.500 |
| Output / 1M | $0.200 | $1.50 |
| Blended (4:1) | $0.200 | $0.700 |
| Status | Available | Available |
| Released | December 2, 2025 | December 2, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 3 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Mistral Large 3 ahead on 1 of 1 counted
Mistral Large 3 ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
Mistral Large 3 ahead on 1 of 2 counted
Ministral 3 14B ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
No shared comparable results for Abstract reasoning, Mathematics, Computer & tool use, Research & search, Long context, Cybersecurity.
Published scores, with matching modes where available. Gaps show Ministral 3 14B relative to Mistral Large 3. Reading the results
| Benchmark | Ministral 3 14B | Mistral Large 3 | Gap |
|---|---|---|---|
| Terminal Bench HardAgentic Development · Accuracy | 4.5Normal · tools | 15.9Normal · tools | −11.4 pts#137 vs #104 of 157 |
| SciCodeScientific Computing · Score | 23.8Normal · no tools | 36.6Normal · no tools | 0.65×#96 vs #82 of 98 |
| GDP.pdfDocuments & Charts · Task pass rate (%) | 1.2Normal · no tools | 1.2Normal · no tools | =#90 vs #90 of 96 |
| MMMU-ProVisual Understanding · Accuracy | 49.8Normal · no tools | 55.7Normal · no tools | −5.9 pts#120 vs #113 of 136 |
| τ³-BankingService Workflows · Score | 6.6Normal · tools | 5.8Normal · tools | 1.14×#101 vs #105 of 120 |
Agentic Development · Accuracy
Scientific Computing · Score
Documents & Charts · Task pass rate (%)
Visual Understanding · Accuracy
Service Workflows · Score
A dash means no result is available.
| Benchmark | Ministral 3 14B | Mistral Large 3 |
|---|---|---|
| Claw Bench | — | 78.6 |
| Pinch Bench | — | 72.2 |
| PinchBench v2 | — | 54.5 |
| Creative Writing | — | 1413 |
| SAGE | — | 24.6 |
| SimpleBench | — | 20.4 |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
Ministral 3 14B costs71%lessthan Mistral Large 3 per million tokens — 3.5× cheaper.Using standard rates at this token mix.
Ministral 3 14B: Standard pricing. Mistral official pricing verified 2026-11-13
Mistral Large 3: Standard pricing. Mistral official pricing verified 2026-11-13; Deprecated 2026-10-31, scheduled retirement 2027-04-30 per docs.mistral.ai/models
| Price / 1M tokens | Ministral 3 14B | Mistral Large 3 | Ratio |
|---|---|---|---|
| Input | $0.20 | $0.50 | 0.40× |
| Output | $0.20 | $1.50 | 0.13× |
| Cached input | — | — | — |
| Cache write | — | — | — |
| Blended | $0.20 | $0.70 | 0.29× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Benchmark | Ministral 3 14B | Mistral Large 3 |
|---|---|---|
| SAGE | Not reported |
| Attribute | Ministral 3 14B | Mistral Large 3 |
|---|---|---|
| Availability | Available | Available |
| Provider | MistralAI | MistralAI |
| Model type | Multimodal model | Multimodal model |
| First release | December 2, 2025 | December 2, 2025 |
| Context window | 256K tokens | 256K tokens |
| Total parameters | 14B | 675B |
| Active parameters | 14B | 41B |
| Architecture | Dense | Mixture of Experts (MoE) |
| Documented capabilities | Reasoning | Reasoning |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
| Weights | Open weights | Open weights |
| Licence | Apache 2.0 | Apache 2.0 |
| Commercial use | Commercial use allowed | Commercial use allowed |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Ministral 3 14B or Mistral Large 3? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.