Multimodal
Like-for-like- MiMo-V2.5
- 58.5
- #29/48
- Qwen3.5 397B
- 62.2
- #27/48
- Basis
- Provisional lane · 2 vs 2 weighted rows
- Reading
- Qwen3.5 397B leads
MiMo-V2.5 vs Qwen3.5 397B
Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
MiMo-V2.5 has the higher public score estimate, 60.72 versus 56.44, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
7 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Long documents
Prompts that approach the documented context limit
MiMo-V2.5
MiMo-V2.5 has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
MiMo-V2.5 and Qwen3.5 397B are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
MiMo-V2.5 and Qwen3.5 397B are scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Qwen3.5 397B does not fit this workload in one request. Qwen3.5 397B has no published cached-input rate, so cached tokens use its listed input rate. MiMo-V2.5 has no comparable published API token rate.
Confidence: rate-fallback
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
8 MiMo-V2.5 only
7 Shared
31 Qwen3.5 397B only
- Shared results
- 7
- MiMo-V2.5 only
- 8
- Qwen3.5 397B only
- 31
- Like-for-like categories
- 1 / 8
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Agentic
Directional only- MiMo-V2.5
- 51.1
- Estimated · #58/151
- Qwen3.5 397B
- 48.2
- Estimated · #78/151
- Basis
- BenchAlign lane · 6 vs 13 public rows
- Reading
- Directional only
Coding
Directional only- MiMo-V2.5
- 54.8
- Estimated · #45/183
- Qwen3.5 397B
- 52.4
- Estimated · #56/183
- Basis
- BenchAlign lane · 4 vs 3 public rows
- Reading
- Directional only
Knowledge
Directional only- MiMo-V2.5
- 53.8
- Estimated · #65/181
- Qwen3.5 397B
- 51.5
- Estimated · #82/181
- Basis
- BenchAlign lane · 2 vs 6 public rows
- Reading
- Directional only
Reasoning
Not comparable- MiMo-V2.5
- Not ranked
- Qwen3.5 397B
- 59.8
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Math
Not comparable- MiMo-V2.5
- Not ranked
- Qwen3.5 397B
- 74.2
- Unranked · 5 rankable rows
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- MiMo-V2.5
- Not ranked
- Qwen3.5 397B
- 69.7
- #5/12
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- MiMo-V2.5
- Not ranked
- Qwen3.5 397B
- 0.0
- #120/120
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | MiMo-V2.5 | Qwen3.5 397B | Basis | Reading |
|---|---|---|---|---|
| Multimodal | 58.5#29/48 | 62.2#27/48 | Like-for-likeProvisional lane · 2 vs 2 weighted rows | Qwen3.5 397B leads |
| Agentic | 51.1Estimated · #58/151 | 48.2Estimated · #78/151 | Directional onlyBenchAlign lane · 6 vs 13 public rows | Directional only |
| Coding | 54.8Estimated · #45/183 | 52.4Estimated · #56/183 | Directional onlyBenchAlign lane · 4 vs 3 public rows | Directional only |
| Knowledge | 53.8Estimated · #65/181 | 51.5Estimated · #82/181 | Directional onlyBenchAlign lane · 2 vs 6 public rows | Directional only |
| Reasoning | Not ranked | 59.8Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Math | Not ranked | 74.2Unranked · 5 rankable rows | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
| Multilingual | Not ranked | 69.7#5/12 | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Instruction following | Not ranked | 0.0#120/120 | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
Terminal-Bench 2.0
Agentic
SWE-bench Pro
Coding
MMMU-Pro
Multimodal
CharXiv
Multimodal
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- MiMo-V2.5
- API rate not published
- Fits in one request
- Qwen3.5 397B
- $0.0024
- Fits in one request
MiMo-V2.5 has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- MiMo-V2.5
- API rate not published
- Fits in one request
- Qwen3.5 397B
- $0.0408
- Fits in one request
MiMo-V2.5 has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- MiMo-V2.5
- API rate not published
- Fits in one request
- Cached-input rate unavailable
- Qwen3.5 397B
- $0.168
- Does not fit in one request
- Cached input priced at the published list-input rate
Qwen3.5 397B does not fit this workload in one request. Qwen3.5 397B has no published cached-input rate, so cached tokens use its listed input rate. MiMo-V2.5 has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationMiMo-V2.5Qwen3.5 397B
Context window
Maximum documented context; output-token limits may be lower.
MiMo-V2.5
1M
Qwen3.5 397B
128K
API model ID
MiMo-V2.5
Not sourced
Qwen3.5 397B
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
MiMo-V2.5
No comparable hosted API rate
Qwen3.5 397B
Not published
Documented inputs
MiMo-V2.5
Not sourced
Qwen3.5 397B
Not sourced
Documented outputs
MiMo-V2.5
Not sourced
Qwen3.5 397B
Not sourced
Provider availability
MiMo-V2.5
Not sourced
Qwen3.5 397B
Not sourced
Reasoning profile
MiMo-V2.5
Reasoning
Qwen3.5 397B
Non-Reasoning
Weight access
MiMo-V2.5
Proprietary
Qwen3.5 397B
Open Weight
License
MiMo-V2.5
Proprietary
Qwen3.5 397B
Open Weight
Release date
MiMo-V2.5
2026-04-22
Qwen3.5 397B
2026-02-16
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- MiMo-V2.5 has the higher public score estimate, 60.72 versus 56.44, but the 90% score intervals overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- MiMo-V2.5 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence46 rows
Agentic
Claw-Eval
Shared sourceMiMo-V2.562.3%Qwen3.5 397B56.8%MiMo-V2.5 leads this result
MM-ClawBench
MiMo-V2.523.8%SourceQwen3.5 397B—Not directly comparable
Terminal-Bench 2.0
MiMo-V2.565.8%SourceQwen3.5 397B52.5%SourceMiMo-V2.5 leads this result
Gert Labs
Shared sourceMiMo-V2.546.89%Qwen3.5 397B46.76%MiMo-V2.5 leads this result
ResearchClawBench
Shared sourceMiMo-V2.516.9%Qwen3.5 397B14.2%MiMo-V2.5 leads this result
Terminal-Bench 2.1 (Vals)
MiMo-V2.560.7%SourceQwen3.5 397B—Not directly comparable
BrowseComp
MiMo-V2.5—Qwen3.5 397B62%SourceNot directly comparable
QwenClawBench
MiMo-V2.5—Qwen3.5 397B51.8%SourceNot directly comparable
τ³-bench results
MiMo-V2.5—Qwen3.5 397B68.4%SourceNot directly comparable
VITA-Bench
MiMo-V2.5—Qwen3.5 397B43.7%SourceNot directly comparable
DeepPlanning
MiMo-V2.5—Qwen3.5 397B37.6%SourceNot directly comparable
Toolathlon
MiMo-V2.5—Qwen3.5 397B36.3%SourceNot directly comparable
MCP Atlas
MiMo-V2.5—Qwen3.5 397B46.1%SourceNot directly comparable
MCP-Tasks
MiMo-V2.5—Qwen3.5 397B74.2%SourceNot directly comparable
WideResearch
MiMo-V2.5—Qwen3.5 397B74.0%SourceNot directly comparable
Coding
SWE-bench Pro
MiMo-V2.556.1%SourceQwen3.5 397B50.9%SourceMiMo-V2.5 leads this result
Terminal-Bench 2.0
MiMo-V2.565.8%SourceQwen3.5 397B—Not directly comparable
LiveCodeBench (Vals)
MiMo-V2.581.5%SourceQwen3.5 397B—Not directly comparable
SWE-bench (Vals)
MiMo-V2.571.0%SourceQwen3.5 397B—Not directly comparable
SWE-bench Verified
MiMo-V2.5—Qwen3.5 397B76.2%SourceNot directly comparable
LiveCodeBench v6
MiMo-V2.5—Qwen3.5 397B83.6%SourceNot directly comparable
Reasoning
Knowledge
GPQA Diamond (Vals)
MiMo-V2.581.6%SourceQwen3.5 397B—Not directly comparable
MMLU-Pro (Vals)
MiMo-V2.582.9%SourceQwen3.5 397B—Not directly comparable
GPQA
MiMo-V2.5—Qwen3.5 397B88.4%SourceNot directly comparable
SuperGPQA
MiMo-V2.5—Qwen3.5 397B70.4%SourceNot directly comparable
MMLU-Pro
MiMo-V2.5—Qwen3.5 397B87.8%SourceNot directly comparable
MMLU-Redux
MiMo-V2.5—Qwen3.5 397B94.9%SourceNot directly comparable
C-Eval
MiMo-V2.5—Qwen3.5 397B93%SourceNot directly comparable
HLE
MiMo-V2.5—Qwen3.5 397B28.7%SourceNot directly comparable
Math
AIME26
MiMo-V2.5—Qwen3.5 397B93.3%SourceNot directly comparable
HMMT Feb 2025
MiMo-V2.5—Qwen3.5 397B94.8%SourceNot directly comparable
HMMT Nov 2025
MiMo-V2.5—Qwen3.5 397B92.7%SourceNot directly comparable
HMMT Feb 2026
MiMo-V2.5—Qwen3.5 397B87.9%SourceNot directly comparable
MMAnswerBench
MiMo-V2.5—Qwen3.5 397B80.9%SourceNot directly comparable
Multilingual
Multimodal
Video-MME (with subtitle)
MiMo-V2.587.7%SourceQwen3.5 397B—Not directly comparable
CharXiv
MiMo-V2.581%SourceQwen3.5 397B80.8%SourceMiMo-V2.5 leads this result
MMMU-Pro
MiMo-V2.577.9%SourceQwen3.5 397B79%SourceQwen3.5 397B leads this result
MathVision
MiMo-V2.5—Qwen3.5 397B88.6%SourceNot directly comparable
VideoMMMU
MiMo-V2.5—Qwen3.5 397B84.7%SourceNot directly comparable
ScreenSpot Pro
MiMo-V2.5—Qwen3.5 397B65.6%SourceNot directly comparable
V*
MiMo-V2.5—Qwen3.5 397B95.8%SourceNot directly comparable
Instruction following
IFEval
MiMo-V2.5—Qwen3.5 397B92.6%SourceNot directly comparable
Frequently asked questions
Which is better, MiMo-V2.5 or Qwen3.5 397B?
MiMo-V2.5 has the higher public score estimate, 60.72 versus 56.44, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, MiMo-V2.5 or Qwen3.5 397B?
MiMo-V2.5 scores higher for coding on the public lane, 54.8 to 52.4. MiMo-V2.5 and Qwen3.5 397B are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, MiMo-V2.5 or Qwen3.5 397B?
MiMo-V2.5 scores higher for agentic tasks on the public lane, 51.1 to 48.2. MiMo-V2.5 and Qwen3.5 397B are scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which costs less, MiMo-V2.5 or Qwen3.5 397B?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, MiMo-V2.5 or Qwen3.5 397B?
MiMo-V2.5 has the larger documented context window: 1M, compared with 128K.
Related comparisons
Last updated September 4, 2026
Watch MiMo-V2.5 vs Qwen3.5 397B
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.