Across 2 comparable benchmarks, DeepSeek-V4-Pro has better reported results on 2 and worse on 0.
Limited evidence2 of 2 shared results countedHow we compare
Price basis: Standard rates vs peak-hour rates. The price section below shows the applicable periods.
| Fact | MAI-Code-1.1-Flash | DeepSeek-V4-Pro |
|---|---|---|
| Context window | 256K tokens | 1M tokens |
| Input / 1M | $0.200 | $1.32 |
| Output / 1M | $1.20 | $3.96 |
| Blended (4:1) | $0.270 | $0.929 |
| Status | Available | Available |
| Released | August 11, 2026 | August 13, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 2 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
DeepSeek-V4-Pro ahead on 2 of 2 counted
No shared comparable results for Abstract reasoning, Mathematics, Science & health, Computer & tool use, Research & search, Long context, Multimodal, Professional work & productivity, Cybersecurity.
Published scores, with matching modes where available. Gaps show MAI-Code-1.1-Flash relative to DeepSeek-V4-Pro. Reading the results
| Benchmark | MAI-Code-1.1-Flash | DeepSeek-V4-Pro | Gap |
|---|---|---|---|
| SWE-bench VerifiedRepository Engineering · Accuracy | 72.6Reported best | 80.6≠Extra-High · tools | −8.0 pts#51 vs #12 of 108 |
| Terminal-Bench 2.1Agentic Development · Accuracy | 62.9Reported best | 72.1≠Extra-High · tools | −9.2 pts#57 vs #47 of 68 |
Repository Engineering · Accuracy
Agentic Development · Accuracy
A dash means no result is available.
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%
MAI-Code-1.1-Flash costs71%lessthan DeepSeek-V4-Pro per million tokens — 3.4× cheaper.Using standard rates vs peak-hour rates at this token mix.
MAI-Code-1.1-Flash: Standard pricing. Microsoft Azure / Foundry official pricing verified 2026-11-13; MAI-Code-1.1-Flash Global Standard
DeepSeek-V4-Pro: Peak-hour pricing. DeepSeek official USD pricing (peak)
| Price / 1M tokens | MAI-Code-1.1-Flash | DeepSeek-V4-Pro | Ratio |
|---|---|---|---|
| Input | $0.20 | $1.32 | 0.15× |
| Output | $1.20 | $3.96 | 0.30× |
| Cached input | $0.02 | $0.044 | 0.45× |
| Cache write | — | — | — |
| Blended | $0.27 | $0.929 | 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 | MAI-Code-1.1-Flash | DeepSeek-V4-Pro |
|---|---|---|
| Agents' Last Exam v1.0 | Not reported | |
| AIME 2026 | Not reported | |
| Code Migration | Not reported | |
| DeepSWE | Not reported | |
| EMB (Excel Modeling) | Not reported | |
| Finance Agent v2 | Not reported | |
| Legal Research Bench | Not reported | |
| MedCode | Not reported | |
| MedScribe | Not reported | |
| ProofBench v1.1 (Lean 4) | Not reported | |
| Public Benefits Bench v1.1 | Not reported | |
| Tax Agent Bench | Not reported | |
| Vibe Code Bench v1.1 | Not reported |
| Attribute | MAI-Code-1.1-Flash | DeepSeek-V4-Pro |
|---|---|---|
| Availability | Available | Available |
| Provider | Microsoft | DeepSeek-AI |
| Model type | Coding model | Reasoning model |
| First release | August 11, 2026 | August 13, 2026 |
| Context window | 256K tokens | 1M tokens |
| Max output | — | 384K tokens |
| Total parameters | 138B | 1.6T |
| Active parameters | 5B | 49B |
| Architecture | Mixture of Experts (MoE) | Mixture of Experts (MoE) |
| Documented capabilities | Coding, Tool use | Reasoning, Multilingual, Coding, Function calling, Tool use, Structured output, Long context |
| Knowledge cutoff | 2025-12 | 2025-05 |
| Input modalities | Text, Image | Text |
| Output modalities | Text | Text |
| Weights | Closed / API only | Open weights |
| Licence | — | MIT License |
| Commercial use | Proprietary | 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 MAI-Code-1.1-Flash or DeepSeek-V4-Pro? 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.