Across 1 comparable benchmark, Qwen4-Max has better reported results on 1 and worse on 0.
Limited evidence1 of 1 shared result countedHow we compare
Mistral Medium 3 is no longer available through its official API. API prices for this version are not shown.
Price basis: Listed rates vs listed rates. The price section below shows the applicable periods.
| Fact | Mistral Medium 3 | Qwen4-Max |
|---|---|---|
| Context window | 128K tokens | 1M tokens |
| Input / 1M | — | $1.50 |
| Output / 1M | — | $4.50 |
| Blended (4:1) | — | $1.07 |
| Status | Retired | Available |
| Released | May 7, 2025 | November 16, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Published scores, with matching modes where available. Gaps show Mistral Medium 3 relative to Qwen4-Max. Reading the results
| Benchmark | Mistral Medium 3 | Qwen4-Max | Gap |
|---|---|---|---|
| HLEKnowledge Exams · Accuracy | 4.5Reported best | 51.7≠Max · no tools | −47.2 pts#147 vs #42 of 151 |
Knowledge Exams · Accuracy
A dash means no result is available.
| Benchmark | Mistral Medium 3 | Qwen4-Max |
|---|---|---|
| DeepSWE | — | 75.7 |
| ProgramBench | — | 31.5 |
| Terminal-Bench 4.0 | — | 48.5 |
| Vibe Code Bench v1.1 | — | 86.7 |
| Agents' Last Exam v1.1 | — | 46.7 |
| APEX-Agents | — | 72.1 |
| AutomationBench-AA | — | 72.5 |
| AA Intelligence Index v5.0.1 | — | 42.9 |
| Agent Arena | — | 7.5 |
| Agent Arena Index | — | 1189 |
| Code Arena WebDev | — | 1750 |
| Vals Index v2.2 | — | 63.2 |
| Chartography | — | 54.2 |
| AA-Briefcase | — | 1686 |
| JobBench | — | 68.5 |
| Legal Research Bench | — | 41.4 |
| Tax Agent Bench | — | 40.4 |
| BioMysteryBench | — | 85.0 |
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%
A blended cost needs a published input and output price on both sides, and one of these two does not have them yet.
Mistral Medium 3: Listed text rates; pricing tier not confirmed.
Qwen4-Max: International pricing. context_length <= 1000000 QwenCloud International (Singapore)
| Price / 1M tokens | Mistral Medium 3 | Qwen4-Max | Ratio |
|---|---|---|---|
| Input | — | $1.50 | — |
| Output | — | $4.50 | — |
| Cached input | — | $0.075 | — |
| Cache write | — | $1.88 | — |
| Blended | — | $1.07 | — |
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 | Mistral Medium 3 | Qwen4-Max |
|---|---|---|
| AA Intelligence Index v5.0.1 | Not reported | |
| Agent Arena Index | Not reported | $1.4079 / task Median · Agent Arena Index rating (index points): 1189 Extra-High (Tools + Internet) |
| Legal Research Bench | Not reported | |
| Tax Agent Bench | Not reported | |
| Terminal-Bench 4.0 | Not reported | $3.90 / task Average · Resolution rate (%): 48.5 Unspecified Reasoning (With Tools) · vals-mini-swe |
| Vals Index v2.2 | Not reported | |
| Vibe Code Bench v1.1 | Not reported |
| Attribute | Mistral Medium 3 | Qwen4-Max |
|---|---|---|
| Availability | Retired | Available |
| Provider | MistralAI | Alibaba |
| Model type | Chat model | Reasoning model |
| First release | May 7, 2025 | November 16, 2026 |
| Context window | 128K tokens | 1M tokens |
| Max output | — | 384K tokens |
| Total parameters | — | 2.4T |
| Active parameters | — | 71B |
| Architecture | Undisclosed | Mixture of Experts (MoE) |
| Documented capabilities | — | Reasoning, Multilingual, Coding, Function calling, Tool use, Structured output, Web search, Long context |
| Input modalities | Text | Text, Image, Video |
| Output modalities | Text | Text |
| Weights | Closed / API only | Closed / API only |
| Commercial use | Proprietary | Proprietary |
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 Mistral Medium 3 or Qwen4-Max? 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.