Multilingual
Like-for-like- Kimi K2.5
- 38.2
- #8/12
- Qwen3.7 Plus
- 78.9
- #3/12
- Basis
- Provisional lane · 1 vs 1 weighted rows
- Reading
- Qwen3.7 Plus leads
Kimi K2.5 vs Qwen3.7 Plus
Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Qwen3.7 Plus has the higher public score estimate, 62.29 versus 55.62, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
20 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
Qwen3.7 Plus
Qwen3.7 Plus 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
Kimi K2.5 and Qwen3.7 Plus 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
Kimi K2.5 is 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
A complete comparable API-rate estimate is not available for both models.
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.
25 Kimi K2.5 only
20 Shared
32 Qwen3.7 Plus only
- Shared results
- 20
- Kimi K2.5 only
- 25
- Qwen3.7 Plus only
- 32
- Like-for-like categories
- 1 / 8
5 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- Kimi K2.5
- 46.0
- Estimated · #90/151
- Qwen3.7 Plus
- 37.7
- Supported · #126/151
- Basis
- BenchAlign lane · 14 vs 11 public rows
- Reading
- Directional only
Coding
Directional only- Kimi K2.5
- 51.5
- Estimated · #64/183
- Qwen3.7 Plus
- 53.1
- Estimated · #51/183
- Basis
- BenchAlign lane · 8 vs 7 public rows
- Reading
- Directional only
Knowledge
Directional only- Kimi K2.5
- 53.1
- Estimated · #70/181
- Qwen3.7 Plus
- 56.8
- Estimated · #50/181
- Basis
- BenchAlign lane · 6 vs 7 public rows
- Reading
- Directional only
Multimodal
Directional only- Kimi K2.5
- 65.7
- #24/48
- Qwen3.7 Plus
- 72.5
- #18/48
- Basis
- Provisional lane · 1 vs 2 weighted rows
- Reading
- Directional only
Instruction following
Directional only- Kimi K2.5
- 85.6
- #40/120
- Qwen3.7 Plus
- 91.1
- #17/120
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Directional only
Reasoning
Not comparable- Kimi K2.5
- 53.5
- Unranked · 3 rankable rows
- Qwen3.7 Plus
- 73.7
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 1 vs 1 weighted rows
- Reading
- Not comparable
Math
Not comparable- Kimi K2.5
- 62.4
- #5/7
- Qwen3.7 Plus
- 78.3
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 4 vs 1 weighted rows
- Reading
- Not comparable
| Category | Kimi K2.5 | Qwen3.7 Plus | Basis | Reading |
|---|---|---|---|---|
| Multilingual | 38.2#8/12 | 78.9#3/12 | Like-for-likeProvisional lane · 1 vs 1 weighted rows | Qwen3.7 Plus leads |
| Agentic | 46.0Estimated · #90/151 | 37.7Supported · #126/151 | Directional onlyBenchAlign lane · 14 vs 11 public rows | Directional only |
| Coding | 51.5Estimated · #64/183 | 53.1Estimated · #51/183 | Directional onlyBenchAlign lane · 8 vs 7 public rows | Directional only |
| Knowledge | 53.1Estimated · #70/181 | 56.8Estimated · #50/181 | Directional onlyBenchAlign lane · 6 vs 7 public rows | Directional only |
| Multimodal | 65.7#24/48 | 72.5#18/48 | Directional onlyProvisional lane · 1 vs 2 weighted rows | Directional only |
| Instruction following | 85.6#40/120 | 91.1#17/120 | Directional onlyProvisional lane · 0 vs 1 weighted rows | Directional only |
| Reasoning | 53.5Unranked · 3 rankable rows | 73.7Unranked · 3 rankable rows | Not comparableProvisional lane · 1 vs 1 weighted rows | Not comparable |
| Math | 62.4#5/7 | 78.3Unranked · 3 rankable rows | Not comparableProvisional lane · 4 vs 1 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
HMMT Feb 2026
Math
HLE
Knowledge
MMLU-ProX
Multilingual
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
- Kimi K2.5
- $0.0021
- Fits in one request
- Qwen3.7 Plus
- API rate not published
- Fits in one request
Qwen3.7 Plus has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Kimi K2.5
- $0.039
- Fits in one request
- Qwen3.7 Plus
- API rate not published
- Fits in one request
Qwen3.7 Plus has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Kimi K2.5
- $0.162
- Fits in one request
- Cached input priced at the published list-input rate
- Qwen3.7 Plus
- API rate not published
- Fits in one request
- Cached-input rate unavailable
Kimi K2.5 has no published cached-input rate, so cached tokens use its listed input rate. Qwen3.7 Plus 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.
SpecificationKimi K2.5Qwen3.7 Plus
Context window
Maximum documented context; output-token limits may be lower.
Kimi K2.5
256K
Qwen3.7 Plus
1M
API model ID
Kimi K2.5
Not sourced
Qwen3.7 Plus
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Kimi K2.5
Not published
Qwen3.7 Plus
No comparable hosted API rate
Documented inputs
Kimi K2.5
Not sourced
Qwen3.7 Plus
Not sourced
Documented outputs
Kimi K2.5
Not sourced
Qwen3.7 Plus
Not sourced
Provider availability
Kimi K2.5
Not sourced
Qwen3.7 Plus
Not sourced
Reasoning profile
Kimi K2.5
Non-Reasoning
Qwen3.7 Plus
Reasoning
Weight access
Kimi K2.5
Open Weight
Qwen3.7 Plus
Proprietary
License
Kimi K2.5
Open Weight
Qwen3.7 Plus
Proprietary
Release date
Kimi K2.5
2026-02-01
Qwen3.7 Plus
2026-06-03
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
- Qwen3.7 Plus has the higher public score estimate, 62.29 versus 55.62, but the 90% score intervals overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Qwen3.7 Plus has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Kimi K2.5
API / mo$2,700
Self-host / mo$5,221
Break-even132M/day
Qwen3.7 Plus
API / mo$0
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence77 rows
Agentic
Terminal-Bench 2.0
Kimi K2.550.8%SourceQwen3.7 Plus70.3%SourceQwen3.7 Plus leads this result
BrowseComp
Kimi K2.560.6%SourceQwen3.7 Plus—Not directly comparable
Claw-Eval
Kimi K2.552.3%SourceQwen3.7 Plus62.7%SourceQwen3.7 Plus leads this result
QwenClawBench
Kimi K2.554.3%SourceQwen3.7 Plus61.8%SourceQwen3.7 Plus leads this result
τ³-bench results
Kimi K2.565.7%SourceQwen3.7 Plus—Not directly comparable
DeepSearchQA
Kimi K2.577.1%SourceQwen3.7 Plus—Not directly comparable
DeepPlanning
Kimi K2.514.4%SourceQwen3.7 Plus62.3%SourceQwen3.7 Plus leads this result
Toolathlon
Kimi K2.527.8%SourceQwen3.7 Plus—Not directly comparable
MCP Atlas
Kimi K2.529.5%SourceQwen3.7 Plus73.2%SourceQwen3.7 Plus leads this result
MCP-Tasks
Kimi K2.559.1%SourceQwen3.7 Plus—Not directly comparable
WideResearch
Kimi K2.572.7%SourceQwen3.7 Plus—Not directly comparable
Gert Labs
Kimi K2.545.88%SourceQwen3.7 Plus—Not directly comparable
ResearchClawBench
Kimi K2.514.0%SourceQwen3.7 Plus—Not directly comparable
JobBench
Kimi K2.58.7%SourceQwen3.7 Plus—Not directly comparable
BFCL v4
Kimi K2.5—Qwen3.7 Plus72.9%SourceNot directly comparable
VITA-Bench
Kimi K2.5—Qwen3.7 Plus45.6%SourceNot directly comparable
OSWorld-Verified
Kimi K2.5—Qwen3.7 Plus73.3%SourceNot directly comparable
AndroidWorld
Kimi K2.5—Qwen3.7 Plus81.0%SourceNot directly comparable
OSWorld 2.0
Kimi K2.5—Qwen3.7 Plus2.8%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
Kimi K2.5—Qwen3.7 Plus52.8%SourceNot directly comparable
Coding
SWE-bench Verified
Kimi K2.576.8%SourceQwen3.7 Plus77.7%SourceQwen3.7 Plus leads this result
SWE-bench Verified*
Kimi K2.570.8%SourceQwen3.7 Plus—Not directly comparable
LiveCodeBench v6
Kimi K2.585.0%SourceQwen3.7 Plus—Not directly comparable
SWE-bench Pro
Kimi K2.550.7%SourceQwen3.7 Plus57.6%SourceQwen3.7 Plus leads this result
SWE Multilingual
Kimi K2.573%SourceQwen3.7 Plus75.8%SourceQwen3.7 Plus leads this result
SWE-Rebench
Kimi K2.558.5%SourceQwen3.7 Plus—Not directly comparable
React Native Evals
Kimi K2.577.2%SourceQwen3.7 Plus—Not directly comparable
SciCode
Kimi K2.548.7%SourceQwen3.7 Plus51.3%SourceQwen3.7 Plus leads this result
Terminal-Bench 2.0
Kimi K2.5—Qwen3.7 Plus70.3%SourceNot directly comparable
NL2Repo
Kimi K2.5—Qwen3.7 Plus41.1%SourceNot directly comparable
LiveCodeBench
Kimi K2.5—Qwen3.7 Plus89.6%SourceNot directly comparable
Reasoning
Knowledge
GPQA
Kimi K2.587.6%SourceQwen3.7 Plus90.3%SourceQwen3.7 Plus leads this result
GPQA-D
Kimi K2.587.6%SourceQwen3.7 Plus90.3%SourceQwen3.7 Plus leads this result
SuperGPQA
Kimi K2.569.2%SourceQwen3.7 Plus71.4%SourceQwen3.7 Plus leads this result
MMLU-Pro
Kimi K2.587.1%SourceQwen3.7 Plus88.5%SourceQwen3.7 Plus leads this result
MMLU-Pro (Arcee)
Kimi K2.587.1%SourceQwen3.7 Plus—Not directly comparable
HLE
Kimi K2.530.1%SourceQwen3.7 Plus34.7%SourceQwen3.7 Plus leads this result
MMLU-Redux
Kimi K2.5—Qwen3.7 Plus94.5%SourceNot directly comparable
MMMLU
Kimi K2.5—Qwen3.7 Plus89.0%SourceNot directly comparable
Math
AIME 2025
Kimi K2.596.1%SourceQwen3.7 Plus—Not directly comparable
AIME26
Kimi K2.595.8%SourceQwen3.7 Plus—Not directly comparable
AIME25 (Arcee)
Kimi K2.596.3%SourceQwen3.7 Plus—Not directly comparable
HMMT Feb 2025
Kimi K2.595.4%SourceQwen3.7 Plus—Not directly comparable
HMMT Nov 2025
Kimi K2.591.1%SourceQwen3.7 Plus—Not directly comparable
HMMT Feb 2026
Kimi K2.587.1%SourceQwen3.7 Plus92.9%SourceQwen3.7 Plus leads this result
MMAnswerBench
Kimi K2.581.8%SourceQwen3.7 Plus—Not directly comparable
FrontierMath v2 (Tiers 1-3)
Kimi K2.527.900%SourceQwen3.7 Plus—Not directly comparable
FrontierMath v2 (Tier 4)
Kimi K2.54.200%SourceQwen3.7 Plus—Not directly comparable
IMOAnswerBench
Kimi K2.5—Qwen3.7 Plus86.0%SourceNot directly comparable
Apex
Kimi K2.5—Qwen3.7 Plus22.7%SourceNot directly comparable
Multilingual
MMLU-ProX
Kimi K2.582.3%SourceQwen3.7 Plus85.4%SourceQwen3.7 Plus leads this result
NOVA-63
Kimi K2.556.0%SourceQwen3.7 Plus58.8%SourceQwen3.7 Plus leads this result
INCLUDE
Kimi K2.5—Qwen3.7 Plus83.0%SourceNot directly comparable
MAXIFE
Kimi K2.5—Qwen3.7 Plus88.8%SourceNot directly comparable
PolyMath
Kimi K2.5—Qwen3.7 Plus84.0%SourceNot directly comparable
Multimodal
MMMU-Pro
Kimi K2.578.5%SourceQwen3.7 Plus79%SourceQwen3.7 Plus leads this result
Video-MME
Kimi K2.587.4%SourceQwen3.7 Plus—Not directly comparable
MMVU
Kimi K2.580.4%SourceQwen3.7 Plus—Not directly comparable
VideoMMMU
Kimi K2.586.6%SourceQwen3.7 Plus85.4%SourceKimi K2.5 leads this result
MathVision
Kimi K2.5—Qwen3.7 Plus90.3%SourceNot directly comparable
CharXiv
Kimi K2.5—Qwen3.7 Plus85.9%SourceNot directly comparable
ERQA
Kimi K2.5—Qwen3.7 Plus69.8%SourceNot directly comparable
MedXpertQA (MM)
Kimi K2.5—Qwen3.7 Plus71.0%SourceNot directly comparable
ScreenSpot Pro
Kimi K2.5—Qwen3.7 Plus79.0%SourceNot directly comparable
SimpleVQA
Kimi K2.5—Qwen3.7 Plus81.7%SourceNot directly comparable
MMSearch-Plus
Kimi K2.5—Qwen3.7 Plus41.4%SourceNot directly comparable
RealWorldQA
Kimi K2.5—Qwen3.7 Plus86.9%SourceNot directly comparable
OmniDocBench 1.5
Kimi K2.5—Qwen3.7 Plus91.4%SourceNot directly comparable
OCRBench V2
Kimi K2.5—Qwen3.7 Plus70.7%SourceNot directly comparable
ODINW13
Kimi K2.5—Qwen3.7 Plus51.1%SourceNot directly comparable
Video-MME (with subtitle)
Kimi K2.5—Qwen3.7 Plus88.0%SourceNot directly comparable
MLVU (M-Avg)
Kimi K2.5—Qwen3.7 Plus87.4%SourceNot directly comparable
Instruction following
Frequently asked questions
Which is better, Kimi K2.5 or Qwen3.7 Plus?
Qwen3.7 Plus has the higher public score estimate, 62.29 versus 55.62, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Kimi K2.5 or Qwen3.7 Plus?
Qwen3.7 Plus scores higher for coding on the public lane, 53.1 to 51.5. Kimi K2.5 and Qwen3.7 Plus 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, Kimi K2.5 or Qwen3.7 Plus?
Kimi K2.5 scores higher for agentic tasks on the public lane, 46 to 37.7. Kimi K2.5 is 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, Kimi K2.5 or Qwen3.7 Plus?
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, Kimi K2.5 or Qwen3.7 Plus?
Qwen3.7 Plus has the larger documented context window: 1M, compared with 256K.
Related comparisons
Last updated September 4, 2026
Watch Kimi K2.5 vs Qwen3.7 Plus
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.