Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs Qwen3 235B A22B Thinking 2507

Claude Haiku 4.5 leads Qwen3 235B A22B Thinking 2507 on the Artificial Analysis Intelligence Index, 16.9 to 12.7, and Qwen3 235B A22B Thinking 2507 costs 1.4x less per output token ($3.50 vs $5.00 per million). Updated October 22, 2026; 43 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace Qwen3 235B A22B Thinking 2507
Claude Haiku 4.5Anthropic
Coding
35.6
Overall
41.0
Output $/M
$5.00
20
Qwen3 235B A22B Thinking 2507Qwen
Coding
No data
Overall
52.9
Output $/M
$3.50
23
vs boards won of 43 shared

Claude Haiku 4.5 or Qwen3 235B A22B Thinking 2507: which to pick

Only Claude Haiku 4.5 has a coding score, 35.6 on the Vibe Coding Index; Qwen3 235B A22B Thinking 2507 has none, so the two cannot be ranked on coding.

Pick Qwen3 235B A22B Thinking 2507 for output tokens 1.4x cheaper ($3.50 vs $5.00 per million) and work measured by GPQA Diamond (Epoch AI run) or LMArena Text: expert, where it leads.

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved taskModel BQwen3 235B A22B Thinking 2507QwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
43
Claude Haiku 4.5 only
55
Qwen3 235B A22B Thinking 2507 only
3
Like-for-like categories
8 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.

At a glance

Coding index
Claude Haiku 4.5 35.6 from 4 benchmarks, Qwen3 235B A22B Thinking 2507 not benchmarked.
Widest category
Web design, 14.5 points apart on average over 6 shared benchmarks.
Widest single gap
SimpleQA Verified: Claude Haiku 4.5 13.2% against Qwen3 235B A22B Thinking 2507 40.4%, 27.2 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against Qwen3 235B A22B Thinking 2507 $3.50 per million output tokens, 1.4x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, Qwen3 235B A22B Thinking 2507 128K.

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.

Boards won, where both have a result
CategoryClaude Haiku 4.5BarsQwen3 235B A22B Thinking 2507Ties
Coding40
Intelligence10
Agentic work20
Reasoning22
Math03
Knowledge05
Web design60
General513
All shared boards2023
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
Coding benchmarks for Claude Haiku 4.5 and Qwen3 235B A22B Thinking 2507
BenchmarkClaude Haiku 4.5Qwen3 235B A22B Thinking 2507Leader
SWE-bench Verified66.6%Not measuredOnly Claude Haiku 4.5 measured
SWE-bench Multilingual64.7%Not measuredOnly Claude Haiku 4.5 measured
LiveBench coding48.1%Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev1330Not measuredOnly Claude Haiku 4.5 measured
AA Coding Index43.922.1Claude Haiku 4.5
LiveCodeBench (Vals AI)41.2%Not measuredOnly Claude Haiku 4.5 measured
SWE-bench Verified (Vals AI)66.6%Not measuredOnly Claude Haiku 4.5 measured
Vibe Code Bench (Vals AI)11.4%Not measuredOnly Claude Haiku 4.5 measured
Code migration (Vals AI)7.5%Not measuredOnly Claude Haiku 4.5 measured
ProgramBench (Vals AI)0.0%Not measuredOnly Claude Haiku 4.5 measured
Terminal-Bench 2.1 (Vals AI)43.8%Not measuredOnly Claude Haiku 4.5 measured
Terminal-Bench35.5%Not measuredOnly Claude Haiku 4.5 measured
WeirdML45.4%41.0%Claude Haiku 4.5
LMArena Text: coding14541424Claude Haiku 4.5
LMArena Text: software and IT14391431Claude Haiku 4.5
LMArena WebDev: React1326Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev: HTML1318Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 26 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Claude Haiku 4.5 and Qwen3 235B A22B Thinking 2507
BenchmarkClaude Haiku 4.5Qwen3 235B A22B Thinking 2507Leader
AA Intelligence Index16.912.7Claude Haiku 4.5
Epoch Capabilities Index142.2Not measuredOnly Claude Haiku 4.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for Claude Haiku 4.5 and Qwen3 235B A22B Thinking 2507
BenchmarkClaude Haiku 4.5Qwen3 235B A22B Thinking 2507Leader
AA Agentic Index8.01.3Claude Haiku 4.5
LiveBench research42.2%Not measuredOnly Claude Haiku 4.5 measured
LiveBench browser40.0%Not measuredOnly Claude Haiku 4.5 measured
LiveBench long agentic11.1%Not measuredOnly Claude Haiku 4.5 measured
Finance Agent (Vals AI)31.0%Not measuredOnly Claude Haiku 4.5 measured
Tax Agent Bench (Vals AI)5.9%Not measuredOnly Claude Haiku 4.5 measured
Legal Research Bench (Vals AI)10.6%Not measuredOnly Claude Haiku 4.5 measured
Excel Modeling Benchmark (Vals AI)22.7%Not measuredOnly Claude Haiku 4.5 measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%Not measuredOnly Claude Haiku 4.5 measured
Vending-Bench 2$459-$11Claude Haiku 4.5
Berkeley Function Calling Leaderboard (BFCL)68.7%Not measuredOnly Claude Haiku 4.5 measured
MCP Atlas40.2%Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index22
Reasoning benchmarks for Claude Haiku 4.5 and Qwen3 235B A22B Thinking 2507
BenchmarkClaude Haiku 4.5Qwen3 235B A22B Thinking 2507Leader
GPQA Diamond72.2%Not measuredOnly Claude Haiku 4.5 measured
LiveBench reasoning61.7%Not measuredOnly Claude Haiku 4.5 measured
MMMU Pro (Vals AI)46.1%Not measuredOnly Claude Haiku 4.5 measured
GPQA Diamond (Epoch AI run)71.2%80.1%Qwen3 235B A22B Thinking 2507
ARC-AGI47.7%Not measuredOnly Claude Haiku 4.5 measured
ARC-AGI-24.0%Not measuredOnly Claude Haiku 4.5 measured
Chess puzzles8.0%Not measuredOnly Claude Haiku 4.5 measured
Mystery game puzzlesNot measured9.0%Only Qwen3 235B A22B Thinking 2507 measured
LMArena Text: hard prompts14211416Claude Haiku 4.5
LMArena Text: expert14431463Qwen3 235B A22B Thinking 2507
LMArena Text: hard prompts in English14351432Claude Haiku 4.5
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Claude Haiku 4.5 and Qwen3 235B A22B Thinking 2507
BenchmarkClaude Haiku 4.5Qwen3 235B A22B Thinking 2507Leader
AIME82.7%Not measuredOnly Claude Haiku 4.5 measured
MGSM (Vals AI)92.2%Not measuredOnly Claude Haiku 4.5 measured
OTIS Mock AIME66.7%86.7%Qwen3 235B A22B Thinking 2507
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981412Qwen3 235B A22B Thinking 2507
LMArena Text: mathematical work14301435Qwen3 235B A22B Thinking 2507
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for Claude Haiku 4.5 and Qwen3 235B A22B Thinking 2507
BenchmarkClaude Haiku 4.5Qwen3 235B A22B Thinking 2507Leader
MMLU Pro78.7%Not measuredOnly Claude Haiku 4.5 measured
LegalBench (Vals AI)81.2%Not measuredOnly Claude Haiku 4.5 measured
CaseLaw (Vals AI)56.5%Not measuredOnly Claude Haiku 4.5 measured
CorpFin (Vals AI)60.6%Not measuredOnly Claude Haiku 4.5 measured
TaxEval (Vals AI)67.5%Not measuredOnly Claude Haiku 4.5 measured
MortgageTax (Vals AI)62.2%Not measuredOnly Claude Haiku 4.5 measured
MedQA (Vals AI)79.6%Not measuredOnly Claude Haiku 4.5 measured
MedCode (Vals AI)32.7%Not measuredOnly Claude Haiku 4.5 measured
SimpleQA Verified13.2%40.4%Qwen3 235B A22B Thinking 2507
LMArena Text: science14061433Qwen3 235B A22B Thinking 2507
LMArena Text: medicine and healthcare13941456Qwen3 235B A22B Thinking 2507
LMArena Text: legal and government14001415Qwen3 235B A22B Thinking 2507
LMArena Text: business and finance14001413Qwen3 235B A22B Thinking 2507
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for Claude Haiku 4.5 and Qwen3 235B A22B Thinking 2507
BenchmarkClaude Haiku 4.5Qwen3 235B A22B Thinking 2507Leader
Design Arena: websites11221052Claude Haiku 4.5
Design Arena: UI components1097942Claude Haiku 4.5
Design Arena: game dev1096956Claude Haiku 4.5
Design Arena: data viz1124950Claude Haiku 4.5
Design Arena: 3D1071997Claude Haiku 4.5
Design Arena: all code categories11141032Claude Haiku 4.5
Design Arena: SVG1025Not measuredOnly Claude Haiku 4.5 measured
Design Arena: ASCII art1140Not measuredOnly Claude Haiku 4.5 measured
LiveBench design59.9%Not measuredOnly Claude Haiku 4.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index513
General benchmarks for Claude Haiku 4.5 and Qwen3 235B A22B Thinking 2507
BenchmarkClaude Haiku 4.5Qwen3 235B A22B Thinking 2507Leader
LiveBench data analysis59.3%Not measuredOnly Claude Haiku 4.5 measured
Public Benefits Bench (Vals AI)54.3%Not measuredOnly Claude Haiku 4.5 measured
SAGE (Vals AI)31.8%Not measuredOnly Claude Haiku 4.5 measured
MedScribe (Vals AI)85.2%Not measuredOnly Claude Haiku 4.5 measured
Vals Multimodal Index42.9%Not measuredOnly Claude Haiku 4.5 measured
DTBench73.6%80.3%Qwen3 235B A22B Thinking 2507
LMCA30.9%29.3%Claude Haiku 4.5
Fiction.LiveBenchNot measured75.0%Only Qwen3 235B A22B Thinking 2507 measured
Creative writing (Lech Mazur)Not measured82.4%Only Qwen3 235B A22B Thinking 2507 measured
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971415Qwen3 235B A22B Thinking 2507
LMArena Text: instruction following14141386Claude Haiku 4.5
LMArena Text: creative writing13711384Qwen3 235B A22B Thinking 2507
LMArena Text: English14141429Qwen3 235B A22B Thinking 2507
LMArena Text: non-English13771397Qwen3 235B A22B Thinking 2507
LMArena Text: Chinese14181481Qwen3 235B A22B Thinking 2507
LMArena Text: German13741408Qwen3 235B A22B Thinking 2507
LMArena Text: Japanese13381386Qwen3 235B A22B Thinking 2507
LMArena Text: Korean13461375Qwen3 235B A22B Thinking 2507
LMArena Text: French1411Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: Spanish14211389Claude Haiku 4.5
LMArena Text: Russian13811401Qwen3 235B A22B Thinking 2507
LMArena Text: Polish13431390Qwen3 235B A22B Thinking 2507
LMArena Text: multi-turn14091406Claude Haiku 4.5
LMArena Text: longer queries14271400Claude Haiku 4.5
LMArena Text: writing and language13861388Qwen3 235B A22B Thinking 2507
LMArena Text: entertainment and media13691370Qwen3 235B A22B Thinking 2507
LMArena Document1420Not measuredOnly Claude Haiku 4.5 measured
MultiChallenge50.5%Not measuredOnly Claude Haiku 4.5 measured
EQ-Bench 41064Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 18 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Haiku 4.5 and Qwen3 235B A22B Thinking 2507
BenchmarkClaude Haiku 4.5Qwen3 235B A22B Thinking 2507Leader
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 4.5$0.0035Fits in one request
Qwen3 235B A22B Thinking 2507$0.0022Fits in one request

Qwen3 235B A22B Thinking 2507 costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
Qwen3 235B A22B Thinking 2507$0.033Fits in one request

Qwen3 235B A22B Thinking 2507 costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
Qwen3 235B A22B Thinking 2507$0.125Exceeds the context window

Qwen3 235B A22B Thinking 2507 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.

Specifications of Claude Haiku 4.5 and Qwen3 235B A22B Thinking 2507
SpecificationAnthropic Claude Haiku 4.5Qwen3 235B A22B Thinking 2507
MakerAnthropicQwen
WeightsNo public weights listedOpen weights
ReleasedOctober 15, 2025July 25, 2025
Context window200K128K
Input $/Mtok$1.00$0.45
Output $/Mtok$5.00$3.50
Coding index35.6Not benchmarked
Independent measurements behind it40
Cost per solved task$0.56Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than Qwen3 235B A22B Thinking 2507 for coding?

Only Claude Haiku 4.5 has a coding score, 35.6 on the Vibe Coding Index; Qwen3 235B A22B Thinking 2507 has none, so the two cannot be ranked on coding. Pick Qwen3 235B A22B Thinking 2507 for output tokens 1.4x cheaper ($3.50 vs $5.00 per million) and work measured by GPQA Diamond (Epoch AI run) or LMArena Text: expert, where it leads.

Which is cheaper, Claude Haiku 4.5 or Qwen3 235B A22B Thinking 2507?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Qwen3 235B A22B Thinking 2507 costs $0.45 and $3.50. Cost per solved task is known for Claude Haiku 4.5 only.

Which has the bigger context window, Claude Haiku 4.5 or Qwen3 235B A22B Thinking 2507?

Claude Haiku 4.5, with 200K tokens against 128K.

How many benchmarks is the Claude Haiku 4.5 vs Qwen3 235B A22B Thinking 2507 comparison based on?

43 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 4.5's coding index rests on 4 independent benchmarks and Qwen3 235B A22B Thinking 2507's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next