Claude Haiku 5.5 vs Kimi K3.1 Pro
Kimi K3.1 Pro leads Claude Haiku 5.5 on coding, 82.2 to 70.8 on the Vibe Coding Index, and Claude Haiku 5.5 costs 20.0x less per output token ($0.50 vs $10.00 per million). Updated October 29, 2026; 34 benchmarks have a result for both.
Claude Haiku 5.5 or Kimi K3.1 Pro: which to pick
Pick Kimi K3.1 Pro for coding: it scores 82.2 on the Vibe Coding Index against 70.8 for Claude Haiku 5.5, though on 4 benchmarks against 5.
Pick Claude Haiku 5.5 for output tokens 20.0x cheaper ($0.50 vs $10.00 per million) and work measured by LiveBench coding or Vibe Code Bench (Vals AI), where it leads.
- Shared results
- 34
- Claude Haiku 5.5 only
- 57
- Kimi K3.1 Pro only
- 1
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
Kimi K3.1 Pro
Kimi K3.1 Pro scores 82.2 against 70.8.
5 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
Kimi K3.1 Pro
Kimi K3.1 Pro leads, 46.0 against 36.2.
Same board, both measured
Web design
Design Arena: websites
Kimi K3.1 Pro
Kimi K3.1 Pro leads, 1325 against 1262.
Same board, both measured
General
Vals Index
Kimi K3.1 Pro
Kimi K3.1 Pro leads, 62.5% against 58.7%.
Same board, both measured
Long documents
Listed context window
Kimi K3.1 Pro
Kimi K3.1 Pro takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Claude Haiku 5.5
Claude Haiku 5.5 $0.0003, Kimi K3.1 Pro $0.0070 per turn.
List prices
At a glance
- Coding index
- Claude Haiku 5.5 70.8 from 5 benchmarks, Kimi K3.1 Pro 82.2 from 4 benchmarks.
- Widest category
- Coding, 13.8 points apart on average over 9 shared benchmarks.
- Widest single gap
- Terminal-Bench 4 (Vals AI): Claude Haiku 5.5 36.4% against Kimi K3.1 Pro 63.6%, 36.4 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 5.5 $0.50 against Kimi K3.1 Pro $10.00 per million output tokens, 20.0x apart.
- Context window
- Claude Haiku 5.5 takes 1M tokens, Kimi K3.1 Pro 1.05M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Claude Haiku 5.5 | Bars | Kimi K3.1 Pro | Ties |
|---|---|---|---|---|
| Coding | 2 | 7 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 4 | 5 | ||
| Reasoning | 1 | 2 | ||
| Math | 0 | 1 | ||
| Web design | 1 | 7 | ||
| General | 0 | 3 | ||
| All shared boards | 8 | 26 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index27
| Benchmark | Claude Haiku 5.5 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| LiveBench coding | 91.4% | 81.8% | Claude Haiku 5.5 |
| LMArena WebDev | 1589 | 1695 | Kimi K3.1 Pro |
| Terminal-Bench 4 (Vals AI) | 36.4% | 63.6% | Kimi K3.1 Pro |
| Vibe Code Bench (Vals AI) | 90.4% | 84.9% | Claude Haiku 5.5 |
| Code migration (Vals AI) | 44.6% | Not measured | Only Claude Haiku 5.5 measured |
| ProgramBench (Vals AI) | 2.5% | Not measured | Only Claude Haiku 5.5 measured |
| IOI (Vals AI) | 47.3% | 81.9% | Kimi K3.1 Pro |
| SWE-bench Multimodal (Vals AI) | 44.0% | Not measured | Only Claude Haiku 5.5 measured |
| Vibe Code Bench 1-100 (Vals AI) | 20.4% | Not measured | Only Claude Haiku 5.5 measured |
| CyberBench (Vals AI) | 75.5% | Not measured | Only Claude Haiku 5.5 measured |
| SciCode | 55.0% | 60.8% | Kimi K3.1 Pro |
| FrontierCode | 46.4% | Not measured | Only Claude Haiku 5.5 measured |
| FrontierSWE | 43.8% | Not measured | Only Claude Haiku 5.5 measured |
| ALE-Bench | 1587.0 | 1932.8 | Kimi K3.1 Pro |
| LMArena Text: coding | 1454 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: software and IT | 1449 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena WebDev: React | 1608 | 1701 | Kimi K3.1 Pro |
| LMArena WebDev: HTML | 1568 | 1706 | Kimi K3.1 Pro |
| SciCode | 9.2% | Not measured | Only Claude Haiku 5.5 measured |
| SWE-Bench Pro V2 | 87.2% | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 23 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Claude Haiku 5.5 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | 36.2 | 46.0 | Kimi K3.1 Pro |
| Epoch Capabilities Index | 159.3 | Not measured | Only Claude Haiku 5.5 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index45
| Benchmark | Claude Haiku 5.5 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| LiveBench research | 81.9% | 77.9% | Claude Haiku 5.5 |
| LiveBench browser | 69.5% | 75.9% | Kimi K3.1 Pro |
| LiveBench long agentic | 40.0% | 39.1% | Claude Haiku 5.5 |
| SREBench (Vals AI) | 5.7% | Not measured | Only Claude Haiku 5.5 measured |
| Finance Agent (Vals AI) | 54.1% | Not measured | Only Claude Haiku 5.5 measured |
| Tax Agent Bench (Vals AI) | 31.9% | 24.9% | Claude Haiku 5.5 |
| Legal Research Bench (Vals AI) | 43.8% | 37.5% | Claude Haiku 5.5 |
| Harvey's Legal Agent Benchmark (Vals AI) | 4.2% | 11.7% | Kimi K3.1 Pro |
| Excel Modeling Benchmark (Vals AI) | 59.0% | Not measured | Only Claude Haiku 5.5 measured |
| BioMysteryBench (Vals AI) | 70.4% | 75.6% | Kimi K3.1 Pro |
| Terminal-Bench-Science (Vals AI) | 10.0% | 31.4% | Kimi K3.1 Pro |
| Vals Science Index | 38.5% | 44.4% | Kimi K3.1 Pro |
| APEX-Agents | 56.1% | Not measured | Only Claude Haiku 5.5 measured |
| Vending-Bench 2 | $3,602 | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 28 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | Claude Haiku 5.5 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| LiveBench reasoning | 82.4% | 91.1% | Kimi K3.1 Pro |
| MysteryMechanism (Vals AI) | 35.1% | 26.1% | Claude Haiku 5.5 |
| Humanity's Last Exam (Artificial Analysis run) | 44.4% | 52.5% | Kimi K3.1 Pro |
| GPQA Diamond (Epoch AI run) | 89.6% | Not measured | Only Claude Haiku 5.5 measured |
| ARC-AGI | 89.0% | Not measured | Only Claude Haiku 5.5 measured |
| ARC-AGI-2 | 61.3% | Not measured | Only Claude Haiku 5.5 measured |
| Chess puzzles | 55.0% | Not measured | Only Claude Haiku 5.5 measured |
| Mystery game puzzles | 30.0% | Not measured | Only Claude Haiku 5.5 measured |
| EBR-bench | 43.8% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: hard prompts | 1421 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: expert | 1454 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: hard prompts in English | 1427 | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 11 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Claude Haiku 5.5 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.9% | Not measured | Only Claude Haiku 5.5 measured |
| FrontierMath, tiers 1 to 3 | 75.1% | Not measured | Only Claude Haiku 5.5 measured |
| FrontierMath, tier 4 | 46.3% | Not measured | Only Claude Haiku 5.5 measured |
| ProofBench | 89.0% | 91.0% | Kimi K3.1 Pro |
| LMArena Text: math | 1434 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: mathematical work | 1438 | Not measured | Only Claude Haiku 5.5 measured |
| MathArena | Not measured | 59.6% | Only Kimi K3.1 Pro measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Claude Haiku 5.5 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| MedCode (Vals AI) | 51.5% | Not measured | Only Claude Haiku 5.5 measured |
| SimpleQA Verified | 23.8% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: science | 1407 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: medicine and healthcare | 1372 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: legal and government | 1391 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: business and finance | 1405 | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 14 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index17
| Benchmark | Claude Haiku 5.5 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| Design Arena: websites | 1262 | 1325 | Kimi K3.1 Pro |
| Design Arena: UI components | 1279 | 1400 | Kimi K3.1 Pro |
| Design Arena: game dev | 1321 | 1410 | Kimi K3.1 Pro |
| Design Arena: data viz | 1287 | 1300 | Kimi K3.1 Pro |
| Design Arena: 3D | 1343 | 1451 | Kimi K3.1 Pro |
| Design Arena: all code categories | 1280 | 1354 | Kimi K3.1 Pro |
| Design Arena: SVG | 1202 | 1328 | Kimi K3.1 Pro |
| LiveBench design | 83.1% | 77.8% | Claude Haiku 5.5 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Claude Haiku 5.5 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| Vals Index | 58.7% | 62.5% | Kimi K3.1 Pro |
| LiveBench data analysis | 53.1% | 79.1% | Kimi K3.1 Pro |
| Public Benefits Bench (Vals AI) | 63.2% | Not measured | Only Claude Haiku 5.5 measured |
| SAGE (Vals AI) | 89.8% | Not measured | Only Claude Haiku 5.5 measured |
| MedScribe (Vals AI) | 89.5% | Not measured | Only Claude Haiku 5.5 measured |
| Long context reasoning (AA-LCR) | 82.7% | 86.3% | Kimi K3.1 Pro |
| DTBench | 95.0% | Not measured | Only Claude Haiku 5.5 measured |
| LMCA | 51.1% | Not measured | Only Claude Haiku 5.5 measured |
| Furniture assembly | 47.5% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text | 1401 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: instruction following | 1415 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: creative writing | 1336 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: English | 1411 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: non-English | 1387 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: Chinese | 1438 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: French | 1430 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: Spanish | 1387 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: Russian | 1370 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: multi-turn | 1398 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: longer queries | 1400 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: writing and language | 1368 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: entertainment and media | 1352 | Not measured | Only Claude Haiku 5.5 measured |
| MultiChallenge | 67.7% | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Haiku 5.5 | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Claude Haiku 5.5 costs less
Repository review
50K input + 3K output tokens
Claude Haiku 5.5 costs less
Agent loop
200K input + 10K output tokens
Claude Haiku 5.5 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Anthropic Claude Haiku 5.5 | MoonshotAI Kimi K3.1 Pro |
|---|---|---|
| Maker | Anthropic | Moonshot AI |
| Weights | No public weights listed | No public weights listed |
| Released | October 7, 2026 | October 23, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $0.10 | $2.00 |
| Output $/Mtok | $0.50 | $10.00 |
| Coding index | 70.8 | 82.2 |
| Independent measurements behind it | 5 | 4 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 5.5 better than Kimi K3.1 Pro for coding?
Pick Kimi K3.1 Pro for coding: it scores 82.2 on the Vibe Coding Index against 70.8 for Claude Haiku 5.5, though on 4 benchmarks against 5. Pick Claude Haiku 5.5 for output tokens 20.0x cheaper ($0.50 vs $10.00 per million) and work measured by LiveBench coding or Vibe Code Bench (Vals AI), where it leads.
Which is cheaper, Claude Haiku 5.5 or Kimi K3.1 Pro?
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; Kimi K3.1 Pro costs $2.00 and $10.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Claude Haiku 5.5 or Kimi K3.1 Pro?
Kimi K3.1 Pro, with 1.05M tokens against 1M.
How many benchmarks is the Claude Haiku 5.5 vs Kimi K3.1 Pro comparison based on?
34 benchmarks have a result for both models as of October 29, 2026. Claude Haiku 5.5's coding index rests on 5 independent benchmarks and Kimi K3.1 Pro's on 4. Where only one model has a result, the page says so instead of naming a winner.