Updated November 6, 2026. Rank says Claude Opus 5.5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Claude Opus 5.5 has the higher public score, 86.32 versus 69.58, and the 90% score intervals do not overlap. 18 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
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.
Code generation, repair, and software-engineering tasks
Claude Opus 5.5
Claude Opus 5.5 has the higher public coding point estimate, 82.8 to 58.9, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Tool use, computer use, and multi-step task completion
Claude Opus 5.5
Claude Opus 5.5 has the higher public agentic point estimate, 89.3 to 66.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Prompts that approach the documented context limit
Kimi K3
Kimi K3 has the larger documented context window.
1K fresh input + 500 output tokens
Kimi K3
Kimi K3 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Kimi K3
Kimi K3 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Kimi K3
Kimi K3 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
Like-for-like · BenchAlign v5.8
Claude Opus 5.5 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
ARC-AGI-2Reasoning
Normalized gap 31.3HLE w/o toolsKnowledge
Normalized gap 20.9AutomationBenchAgentic
Normalized gap 9.2OfficeQA ProMultimodal
Normalized gap 4.4Each row shows the public-lane category score for both models: the BenchAlign v5.8 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.
| Category | Claude Opus 5.5 | Kimi K3 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 89.3Supported · #1/131 | 66.6Supported · #14/131 | Like-for-likeBenchAlign v5.8 lane · 17 vs 18 public rows | Claude Opus 5.5 leads |
| Coding | 82.8Supported · #1/157 | 58.9Supported · #21/157 | Like-for-likeBenchAlign v5.8 lane · 13 vs 17 public rows | Claude Opus 5.5 leads |
| Reasoning | 84.4#4/25 | 68.0#14/25 | Like-for-likeProvisional lane · 1 vs 1 weighted rows | Claude Opus 5.5 leads |
| Knowledge | 89.4Supported · #1/178 | 67.5Supported · #23/178 | Like-for-likeBenchAlign v5.8 lane · 16 vs 6 public rows | Claude Opus 5.5 leads |
| Multimodal | 91.6#3/59 | 89.8#6/59 | Directional onlyProvisional lane · 1 vs 3 weighted rows | Directional only |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 93.8Unranked · 4 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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.
1K fresh input + 500 output tokens
Kimi K3 has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Kimi K3 has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Kimi K3 has the lower modeled cost
Costs use the listed standard API rates.
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
Claude Opus 5.5
Kimi K3
1.05M
Claude Opus 5.5
claude-opus-5-5
Anthropic Claude Opus 5.5 model documentationKimi K3
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Opus 5.5
$0.2 per 1M cached input tokens
Claude Opus 5.5 model documentationKimi K3
$0.3 per 1M cached input tokens
Claude Opus 5.5
Kimi K3
Not sourced
Claude Opus 5.5
Kimi K3
Not sourced
Claude Opus 5.5
Generally Available · Claude API, Amazon Bedrock, Google Cloud, Microsoft Foundry, Claude Platform on AWS
Anthropic Claude Opus 5.5 model documentationKimi K3
Not sourced
Claude Opus 5.5
Reasoning
Kimi K3
Reasoning
Claude Opus 5.5
Proprietary
Kimi K3
Open Weight
Claude Opus 5.5
Proprietary
Kimi K3
Open Weight
Claude Opus 5.5
2026-09-22
Kimi K3
2026-07-16
Claude Opus 5.5 has the higher public score, 86.32 versus 69.58, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
Claude Opus 5.5 has the higher public coding point estimate, 82.8 to 58.9, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Claude Opus 5.5 has the higher public agentic tasks point estimate, 89.3 to 66.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
For the stated presets, chat costs $0.014 on Claude Opus 5.5 and $0.0105 on Kimi K3; repository review costs $0.26 and $0.195; the cache-heavy agent loop costs $0.32 and $0.27. Costs use the listed standard API rates.
Kimi K3 has the larger documented context window: 1.05M, compared with 1M.
Estimates at 50,000 req/day · 1000 tokens/req average.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 4.0
Not directly comparable
Terminal-Bench-Science 0.1
Not directly comparable
AutomationBench
Claude Opus 5.5 leads this result
HLE w/ tools
Not directly comparable
OSWorld 2.0
Not directly comparable
LAB all-pass (Harvey held-out)
Not directly comparable
LAB criterion-pass (Harvey held-out)
Not directly comparable
Toolathlon-Verified
Claude Opus 5.5 leads this result
Toolathlon Verified Pass@3
Not directly comparable
Toolathlon Verified Pass³
Not directly comparable
Toolathlon Verified avg. turns
Not directly comparable
CWE-bench v1
Not directly comparable
Hermes Index
Shared sourceClaude Opus 5.5 leads this result
Hermes Bench
Shared sourceClaude Opus 5.5 leads this result
MazeBench
Claude Opus 5.5 leads this result
OSWorld 2.1
Not directly comparable
OSWorld 2.1 Offline
Not directly comparable
Finch
Not directly comparable
b3 Agent Security
Not directly comparable
Cyber Misuse Refusal
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
BrowseComp
Not directly comparable
DeepSearchQA
Not directly comparable
MCP Atlas
Not directly comparable
JobBench
Not directly comparable
APEX-Agents
Not directly comparable
SpreadsheetBench 2
Not directly comparable
DECK-Bench
Not directly comparable
Terminal-Bench 2.1 (Vals)
Not directly comparable
ApprenticeBench
Not directly comparable
ScarfBench
Shared sourceClaude Opus 5.5 leads this result
FrontierCode 1.1 Main
Not directly comparable
CursorBench 4.0
Not directly comparable
SWE-bench Pro
Not directly comparable
SWE Multilingual
Not directly comparable
SWE Multimodal
Not directly comparable
DeepSWE
Claude Opus 5.5 leads this result
FrontierCode 1.1 Extended
Not directly comparable
FrontierSWE v2
Shared sourceClaude Opus 5.5 leads this result
ProgramBench
Claude Opus 5.5 leads this result
PostTrainBench v1.1
Claude Opus 5.5 leads this result
Bug Hunt Bench
Shared sourceClaude Opus 5.5 leads this result
FrontierCode 2.0
Shared sourceClaude Opus 5.5 leads this result
CursorBench 3.2
Not directly comparable
FrontierSWE
Not directly comparable
Kimi Code Bench v2
Not directly comparable
sweMarathon
Not directly comparable
PostTrain Bench
Not directly comparable
MLS-Bench Lite
Not directly comparable
VulcanBench v3
Not directly comparable
OpenHarmony Bench
Not directly comparable
LiveCodeBench (Vals)
Not directly comparable
SWE-bench (Vals)
Not directly comparable
STEMBench
Not directly comparable
ARC-AGI-1
Claude Opus 5.5 leads this result
ARC-AGI-2
Claude Opus 5.5 leads this result
GraphWalks BFS 256K–1M
Not directly comparable
ExtractBench Pro
Not directly comparable
ExtractBench (LlamaIndex)
Shared sourceClaude Opus 5.5 leads this result
ParseBench
Not directly comparable
Chartography (tools)
Not directly comparable
Chartography (no tools)
Not directly comparable
BenchCAD Vision2Code (no tools)
Not directly comparable
BenchCAD Vision2Code (tools)
Not directly comparable
Biomedical image analysis
Not directly comparable
OfficeQA
Not directly comparable
OfficeQA Pro
Claude Opus 5.5 leads this result
MMMU-Pro
Not directly comparable
MMMU-Pro w/ Python
Not directly comparable
CharXiv w/o tools
Not directly comparable
CharXiv
Not directly comparable
MathVision
Not directly comparable
MathVision w/ Python
Not directly comparable
BabyVision w/ Python
Not directly comparable
ZeroBench
Not directly comparable
ZeroBench w/ Python
Not directly comparable
WorldVQA ForceAnswer
Not directly comparable
OmniDocBench
Not directly comparable
PerceptionBench
Not directly comparable
HLE w/o tools
Claude Opus 5.5 leads this result
HealthBench (raw)
Not directly comparable
HealthBench (length-adjusted)
Not directly comparable
HealthBench Professional
Not directly comparable
HealthBench Professional (raw)
Not directly comparable
BioMysteryBench (human-solvable)
Not directly comparable
BioMysteryBench (human-difficult)
Not directly comparable
SpatialBench Verified
Not directly comparable
SingleCellBench
Not directly comparable
Morphology-to-molecule matching
Not directly comparable
Medicinal chemistry
Not directly comparable
Protein Design
Not directly comparable
Protein Design library ranking
Not directly comparable
De novo protein-binder design
Not directly comparable
Protocols (troubleshooting)
Not directly comparable
Protocols (understanding)
Not directly comparable
GPQA
Not directly comparable
GPQA-D
Not directly comparable
HLE
Not directly comparable
GPQA Diamond (Vals)
Not directly comparable
MMLU-Pro (Vals)
Not directly comparable
Gray Swan IPI (15 attempts)
Shared sourceClaude Opus 5.5 leads this result
ArXivMath Aug. 2026 (no tools)
Not directly comparable
ArXivMath Aug. 2026 (tools)
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Not directly comparable
FrontierMath v2 (Tier 4)
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 6,100+ subscribers.
Last updated November 6, 2026
