Agentic
Like-for-like- GLM-5.1
- 65.4
- Kimi K2.5 (Reasoning)
- 55.0
- Weighted basis
- 2 vs 2 rows
- Reading
- GLM-5.1 leads
Model comparison
GLM-5.1 vs Kimi K2.5 (Reasoning)
Updated August 7, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
GLM-5.1 has the higher public score estimate, 66.9 versus 58.53, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
4 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
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.
Agentic work
Tool use, computer use, and multi-step task completion
GLM-5.1
GLM-5.1 leads on the same 2 weighted benchmark rows.
Confidence: limited
Long documents
Prompts that approach the documented context limit
Kimi K2.5 (Reasoning)
Kimi K2.5 (Reasoning) has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Kimi K2.5 (Reasoning)
Kimi K2.5 (Reasoning) has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Kimi K2.5 (Reasoning)
Kimi K2.5 (Reasoning) has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
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. GLM-5.1 does not fit this workload in one request. GLM-5.1 has no published cached-input rate, so cached tokens use its listed input rate. Kimi K2.5 (Reasoning) has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
16 GLM-5.1 only
4 Shared
5 Kimi K2.5 (Reasoning) only
- Shared results
- 4
- GLM-5.1 only
- 16
- Kimi K2.5 (Reasoning) only
- 5
- Like-for-like categories
- 1 / 8
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Coding
Not comparable- GLM-5.1
- 61.3
- Kimi K2.5 (Reasoning)
- 76.8
- Weighted basis
- 2 vs 1 rows
- Reading
- Not comparable
Reasoning
Not comparable- GLM-5.1
- Not measured
- Kimi K2.5 (Reasoning)
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- GLM-5.1
- 52.3
- Kimi K2.5 (Reasoning)
- 87.2
- Weighted basis
- 1 vs 2 rows
- Reading
- Not comparable
Math
Not comparable- GLM-5.1
- 62.0
- Kimi K2.5 (Reasoning)
- Not measured
- Weighted basis
- 4 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-5.1
- Not measured
- Kimi K2.5 (Reasoning)
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-5.1
- Not measured
- Kimi K2.5 (Reasoning)
- 78.5
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Instruction following
Not comparable- GLM-5.1
- Not measured
- Kimi K2.5 (Reasoning)
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | GLM-5.1 | Kimi K2.5 (Reasoning) | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 65.4 | 55.0 | Like-for-like2 vs 2 rows | GLM-5.1 leads |
| Coding | 61.3 | 76.8 | Not comparable2 vs 1 rows | Not comparable |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Knowledge | 52.3 | 87.2 | Not comparable1 vs 2 rows | Not comparable |
| Math | 62.0 | Not measured | Not comparable4 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | Not measured | 78.5 | Not comparable0 vs 1 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
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
GLM-5.1: 63.5%Kimi K2.5 (Reasoning): 50.8%Normalized gap 12.7GLM-5.1 source Kimi K2.5 (Reasoning) sourceBrowseComp
Agentic
GLM-5.1: 68%Kimi K2.5 (Reasoning): 60.6%Normalized gap 7.4GLM-5.1 source Kimi K2.5 (Reasoning) source
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
- GLM-5.1
- $0.0036
- Fits in one request
- Kimi K2.5 (Reasoning)
- $0.0021
- Fits in one request
Kimi K2.5 (Reasoning) has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- GLM-5.1
- $0.0832
- Fits in one request
- Kimi K2.5 (Reasoning)
- $0.039
- Fits in one request
Kimi K2.5 (Reasoning) has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GLM-5.1
- $0.352
- Does not fit in one request
- Cached input priced at the published list-input rate
- Kimi K2.5 (Reasoning)
- $0.162
- Fits in one request
- Cached input priced at the published list-input rate
GLM-5.1 does not fit this workload in one request. GLM-5.1 has no published cached-input rate, so cached tokens use its listed input rate. Kimi K2.5 (Reasoning) has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGLM-5.1Kimi K2.5 (Reasoning)
Context window
Maximum documented context; output-token limits may be lower.
GLM-5.1
203K
Kimi K2.5 (Reasoning)
256K
API model ID
GLM-5.1
Not sourced
Kimi K2.5 (Reasoning)
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GLM-5.1
Not published
Kimi K2.5 (Reasoning)
Not published
Documented inputs
GLM-5.1
Not sourced
Kimi K2.5 (Reasoning)
Not sourced
Documented outputs
GLM-5.1
Not sourced
Kimi K2.5 (Reasoning)
Not sourced
Provider availability
GLM-5.1
Not sourced
Kimi K2.5 (Reasoning)
Not sourced
Reasoning profile
GLM-5.1
Reasoning
Kimi K2.5 (Reasoning)
Reasoning
Weight access
GLM-5.1
Open Weight
Kimi K2.5 (Reasoning)
Proprietary
License
GLM-5.1
Open Weight
Kimi K2.5 (Reasoning)
Proprietary
Release date
GLM-5.1
2026-04-07
Kimi K2.5 (Reasoning)
2026-02-01
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
- GLM-5.1 has the higher public score estimate, 66.9 versus 58.53, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.0832 vs $0.039. Cache-heavy agent loop: $0.352 vs $0.162.
- Context tradeoff
- Kimi K2.5 (Reasoning) has the larger documented window (256K).
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.
GLM-5.1
API / mo$4,350
Self-host / mo$18,221
Break-even264M/day
Kimi K2.5 (Reasoning)
API / mo$2,700
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 evidence25 rows
Agentic
Terminal-Bench 2.0
GLM-5.163.5%SourceKimi K2.5 (Reasoning)50.8%SourceGLM-5.1 leads this result
BrowseComp
GLM-5.168%SourceKimi K2.5 (Reasoning)60.6%SourceGLM-5.1 leads this result
τ³-bench results
GLM-5.170.6%SourceKimi K2.5 (Reasoning)—Not directly comparable
MCP Atlas
GLM-5.171.8%SourceKimi K2.5 (Reasoning)—Not directly comparable
CyberGym
GLM-5.168.7%SourceKimi K2.5 (Reasoning)—Not directly comparable
Claw-Eval
GLM-5.162.3%SourceKimi K2.5 (Reasoning)—Not directly comparable
Gert Labs
Shared sourceGLM-5.160.11%Kimi K2.5 (Reasoning)32.58%GLM-5.1 leads this result
ResearchClawBench
GLM-5.118.2%SourceKimi K2.5 (Reasoning)—Not directly comparable
Coding
SWE-bench Pro
GLM-5.158.4%SourceKimi K2.5 (Reasoning)—Not directly comparable
NL2Repo
GLM-5.142.7%SourceKimi K2.5 (Reasoning)—Not directly comparable
SWE-Rebench
GLM-5.162.7%SourceKimi K2.5 (Reasoning)—Not directly comparable
Vibe Code Bench
Shared sourceGLM-5.131.46%Kimi K2.5 (Reasoning)17.54%GLM-5.1 leads this result
SWE-bench Verified
GLM-5.1—Kimi K2.5 (Reasoning)76.8%SourceNot directly comparable
Knowledge
Math
AIME26
GLM-5.195.3%SourceKimi K2.5 (Reasoning)—Not directly comparable
HMMT Nov 2025
GLM-5.194.0%SourceKimi K2.5 (Reasoning)—Not directly comparable
HMMT Feb 2026
GLM-5.182.6%SourceKimi K2.5 (Reasoning)—Not directly comparable
MMAnswerBench
GLM-5.183.8%SourceKimi K2.5 (Reasoning)—Not directly comparable
FrontierMath v2 (Tiers 1-3)
GLM-5.133.448%SourceKimi K2.5 (Reasoning)—Not directly comparable
FrontierMath v2 (Tier 4)
GLM-5.112.500%SourceKimi K2.5 (Reasoning)—Not directly comparable
AIME 2025
GLM-5.1—Kimi K2.5 (Reasoning)96.1%SourceNot directly comparable
Multimodal
MMMU-Pro
GLM-5.1—Kimi K2.5 (Reasoning)78.5%SourceNot directly comparable
Frequently asked questions
Which is better, GLM-5.1 or Kimi K2.5 (Reasoning)?
GLM-5.1 has the higher public score estimate, 66.9 versus 58.53, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, GLM-5.1 or Kimi K2.5 (Reasoning)?
The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.
Which is better for agentic tasks, GLM-5.1 or Kimi K2.5 (Reasoning)?
GLM-5.1 leads the like-for-like agentic tasks comparison across 2 shared weighted benchmark rows.
Which costs less, GLM-5.1 or Kimi K2.5 (Reasoning)?
For the stated presets, chat costs $0.0036 on GLM-5.1 and $0.0021 on Kimi K2.5 (Reasoning); repository review costs $0.0832 and $0.039; the cache-heavy agent loop costs $0.352 and $0.162. GLM-5.1 does not fit this workload in one request. GLM-5.1 has no published cached-input rate, so cached tokens use its listed input rate. Kimi K2.5 (Reasoning) has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, GLM-5.1 or Kimi K2.5 (Reasoning)?
Kimi K2.5 (Reasoning) has the larger documented context window: 256K, compared with 203K.
Related comparisons
Last updated August 7, 2026
Watch GLM-5.1 vs Kimi K2.5 (Reasoning)
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.