Agentic
Not comparable- GPT-5.1-Codex-Max
- Not measured
- Kimi K2.6
- 73.5
- Weighted basis
- 0 vs 3 rows
- Reading
- Not comparable
GPT-5.1-Codex-Max vs Kimi K2.6
Updated August 27, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Kimi K2.6 has the higher public score estimate, 60.14 versus 55.1, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
1 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.
Long documents
Prompts that approach the documented context limit
GPT-5.1-Codex-Max
GPT-5.1-Codex-Max has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Kimi K2.6
Kimi K2.6 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
GPT-5.1-Codex-Max
GPT-5.1-Codex-Max has the lower estimated token cost for this stated workload. Kimi K2.6 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Kimi K2.6
Kimi K2.6 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
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
1 Shared
31 Kimi K2.6 only
- Shared results
- 1
- GPT-5.1-Codex-Max only
- 0
- Kimi K2.6 only
- 31
- Like-for-like categories
- 0 / 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- GPT-5.1-Codex-Max
- Not measured
- Kimi K2.6
- 64.4
- Weighted basis
- 0 vs 3 rows
- Reading
- Not comparable
Reasoning
Not comparable- GPT-5.1-Codex-Max
- Not measured
- Kimi K2.6
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- GPT-5.1-Codex-Max
- Not measured
- Kimi K2.6
- 42.2
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
Math
Not comparable- GPT-5.1-Codex-Max
- Not measured
- Kimi K2.6
- 67.1
- Weighted basis
- 0 vs 4 rows
- Reading
- Not comparable
Multilingual
Not comparable- GPT-5.1-Codex-Max
- Not measured
- Kimi K2.6
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- GPT-5.1-Codex-Max
- Not measured
- Kimi K2.6
- 79.8
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
Instruction following
Not comparable- GPT-5.1-Codex-Max
- Not measured
- Kimi K2.6
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | GPT-5.1-Codex-Max | Kimi K2.6 | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | Not measured | 73.5 | Not comparable0 vs 3 rows | Not comparable |
| Coding | Not measured | 64.4 | Not comparable0 vs 3 rows | Not comparable |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Knowledge | Not measured | 42.2 | Not comparable0 vs 2 rows | Not comparable |
| Math | Not measured | 67.1 | Not comparable0 vs 4 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | Not measured | 79.8 | Not comparable0 vs 2 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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
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
- GPT-5.1-Codex-Max
- $0.00625
- Fits in one request
- Kimi K2.6
- $0.00295
- Fits in one request
Kimi K2.6 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- GPT-5.1-Codex-Max
- $0.0925
- Fits in one request
- Kimi K2.6
- $0.0595
- Fits in one request
Kimi K2.6 has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GPT-5.1-Codex-Max
- $0.15
- Fits in one request
- Kimi K2.6
- $0.249
- Fits in one request
- Cached input priced at the published list-input rate
GPT-5.1-Codex-Max has the lower modeled cost
Kimi K2.6 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.
SpecificationGPT-5.1-Codex-MaxKimi K2.6
Context window
Maximum documented context; output-token limits may be lower.
GPT-5.1-Codex-Max
Kimi K2.6
256K
API model ID
GPT-5.1-Codex-Max
Not sourced
Kimi K2.6
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT-5.1-Codex-Max
$0.125 per 1M cached input tokens
OpenAI GPT-5.1-Codex-Max model documentationKimi K2.6
Not published
Documented inputs
GPT-5.1-Codex-Max
Not sourced
Kimi K2.6
Not sourced
Documented outputs
GPT-5.1-Codex-Max
Not sourced
Kimi K2.6
Not sourced
Provider availability
GPT-5.1-Codex-Max
Not sourced
Kimi K2.6
Not sourced
Reasoning profile
GPT-5.1-Codex-Max
Reasoning
Kimi K2.6
Reasoning
Weight access
GPT-5.1-Codex-Max
Proprietary
Kimi K2.6
Open Weight
License
GPT-5.1-Codex-Max
Proprietary
Kimi K2.6
Open Weight
Release date
GPT-5.1-Codex-Max
2025-11-19
Kimi K2.6
2026-04-20
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
- Kimi K2.6 has the higher public score estimate, 60.14 versus 55.1, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.0925 vs $0.0595. Cache-heavy agent loop: $0.15 vs $0.249.
- Context tradeoff
- GPT-5.1-Codex-Max has the larger documented window (400K).
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.
GPT-5.1-Codex-Max
API / mo$8,438
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Kimi K2.6
API / mo$3,713
Self-host / mo$18,221
Break-even326M/day
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence32 rows
Agentic
Terminal-Bench 2.0
GPT-5.1-Codex-Max—Kimi K2.666.7%SourceNot directly comparable
BrowseComp
GPT-5.1-Codex-Max—Kimi K2.683.2%SourceNot directly comparable
OSWorld-Verified
GPT-5.1-Codex-Max—Kimi K2.673.1%SourceNot directly comparable
Toolathlon
GPT-5.1-Codex-Max—Kimi K2.650%SourceNot directly comparable
MCP Atlas
GPT-5.1-Codex-Max—Kimi K2.655.9%SourceNot directly comparable
Claw-Eval
GPT-5.1-Codex-Max—Kimi K2.662.3%SourceNot directly comparable
DeepSearchQA
GPT-5.1-Codex-Max—Kimi K2.692.5%SourceNot directly comparable
WideResearch
GPT-5.1-Codex-Max—Kimi K2.680.8%SourceNot directly comparable
Gert Labs
GPT-5.1-Codex-Max—Kimi K2.656.82%SourceNot directly comparable
ResearchClawBench
GPT-5.1-Codex-Max—Kimi K2.618.0%SourceNot directly comparable
OSWorld 2.0
GPT-5.1-Codex-Max—Kimi K2.64.6%SourceNot directly comparable
Coding
Vibe Code Bench
Shared sourceGPT-5.1-Codex-Max22.17%Kimi K2.637.89%Kimi K2.6 leads this result
SWE-bench Verified
GPT-5.1-Codex-Max—Kimi K2.680.2%SourceNot directly comparable
LiveCodeBench v6
GPT-5.1-Codex-Max—Kimi K2.689.6%SourceNot directly comparable
SWE-bench Pro
GPT-5.1-Codex-Max—Kimi K2.658.6%SourceNot directly comparable
SWE Multilingual
GPT-5.1-Codex-Max—Kimi K2.676.7%SourceNot directly comparable
SciCode
GPT-5.1-Codex-Max—Kimi K2.652.2%SourceNot directly comparable
Terminal-Bench 2.0
GPT-5.1-Codex-Max—Kimi K2.666.7%SourceNot directly comparable
cursorBench31
GPT-5.1-Codex-Max—Kimi K2.647.6%SourceNot directly comparable
Knowledge
Math
AIME26
GPT-5.1-Codex-Max—Kimi K2.696.4%SourceNot directly comparable
HMMT Feb 2026
GPT-5.1-Codex-Max—Kimi K2.692.7%SourceNot directly comparable
MMAnswerBench
GPT-5.1-Codex-Max—Kimi K2.686.0%SourceNot directly comparable
FrontierMath v2 (Tiers 1-3)
GPT-5.1-Codex-Max—Kimi K2.638.966%SourceNot directly comparable
FrontierMath v2 (Tier 4)
GPT-5.1-Codex-Max—Kimi K2.614.580%SourceNot directly comparable
Multimodal
MMMU-Pro
GPT-5.1-Codex-Max—Kimi K2.679.4%SourceNot directly comparable
MMMU-Pro w/ Python
GPT-5.1-Codex-Max—Kimi K2.680.1%SourceNot directly comparable
CharXiv
GPT-5.1-Codex-Max—Kimi K2.680.4%SourceNot directly comparable
MathVision
GPT-5.1-Codex-Max—Kimi K2.687.4%SourceNot directly comparable
V*
GPT-5.1-Codex-Max—Kimi K2.696.9%SourceNot directly comparable
Frequently asked questions
Which is better, GPT-5.1-Codex-Max or Kimi K2.6?
Kimi K2.6 has the higher public score estimate, 60.14 versus 55.1, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, GPT-5.1-Codex-Max or Kimi K2.6?
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, GPT-5.1-Codex-Max or Kimi K2.6?
The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.
Which costs less, GPT-5.1-Codex-Max or Kimi K2.6?
For the stated presets, chat costs $0.00625 on GPT-5.1-Codex-Max and $0.00295 on Kimi K2.6; repository review costs $0.0925 and $0.0595; the cache-heavy agent loop costs $0.15 and $0.249. Kimi K2.6 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, GPT-5.1-Codex-Max or Kimi K2.6?
GPT-5.1-Codex-Max has the larger documented context window: 400K, compared with 256K.
Related comparisons
Last updated August 27, 2026
Watch GPT-5.1-Codex-Max vs Kimi K2.6
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.