Head-to-head comparison

Claude Haiku 5.5 vs. Muse Wonder

Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.

shared result series: 157
distinct benchmarks: 18
latest retrieval: 2026-10-15

First modelSecond model

Specifications

General specifications

Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.

Specifications for Claude Haiku 5.5 and Muse Wonder
Attribute	Claude Haiku 5.5	Muse Wonder
Provider	Anthropic	Meta
Released	Oct 7, 2026	Oct 12, 2026
Availability	Active	Preview
Model type	Proprietary	Proprietary
Parameters	Not published	Not published
Architecture	Not published	Not published
Context window	1,000,000 tokens	1,048,576 tokens
Knowledge cutoff	June 2026	Not published
Technical sources	Model	Model, Context

Pricing

API pricing compared

The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

API pricing for Claude Haiku 5.5 and Muse Wonder
Price type	Claude Haiku 5.5	Muse Wonder
API input	$0.1 ≤100K / $0.5 >100K	$4
API output	$0.5 ≤100K / $2.5 >100K	$20
Cache read	$0.01 ≤100K / $0.05 >100K	$0.2
Cache write (5 min.)	$0.125 ≤100K / $0.625 >100K	Not listed
Cache write (1 hr.)	$0.2 ≤100K / $1 >100K	Not listed
Price verified	10/13/2026 Source	10/15/2026 Source

Claude Haiku 5.5Muse Wonder

API inputUSD per 1M tokens, base tier

Claude Haiku 5.5$0.1

Muse Wonder$4

API outputUSD per 1M tokens, base tier

Claude Haiku 5.5$0.5

Muse Wonder$20

Cache readUSD per 1M tokens, base tier

Claude Haiku 5.5$0.01

Muse Wonder$0.2

Key to the marks:better valuebetter, but not conclusivetie

Pricing by provider

Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.

No provider tariff for Muse Wonder is available in the stored OpenRouter snapshot. The official direct price is still shown.

Provider pricing for Claude Haiku 5.5 and Muse Wonder
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Claude Haiku 5.5	Anthropic	Direct from developerUp to 100,000 context tokens	$0.1	Lowest listed price: $0.5	Source10/13/2026
	Anthropic	Direct from developerAbove 100,000 context tokens	$0.5	$2.5	Source10/13/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock	Lowest listed price: $0.1	Lowest listed price: $0.5	Source10/16/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/eu-west-1	$0.11	$0.55	Source10/16/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/us-east-1	$0.11	$0.55	Source10/16/2026
	Anthropic	Via OpenRouteranthropic	Lowest listed price: $0.1	Lowest listed price: $0.5	Source10/16/2026
	Azure	Via OpenRouterazure/global	Lowest listed price: $0.1	Lowest listed price: $0.5	Source10/16/2026
	Azure	Via OpenRouterazure/us	$0.11	$0.55	Source10/16/2026
	Claude Platform on AWS	Via OpenRouterclaude-on-aws	Lowest listed price: $0.1	Lowest listed price: $0.5	Source10/16/2026
	Google	Via OpenRoutergoogle-vertex/europe	$0.11	$0.55	Source10/16/2026
	Google	Via OpenRoutergoogle-vertex/global	Lowest listed price: $0.1	Lowest listed price: $0.5	Source10/16/2026
	Google	Via OpenRoutergoogle-vertex/us	$0.11	$0.55	Source10/16/2026
Muse Wonder	Meta	Direct from developerStandard API	Lowest listed price: $4	Lowest listed price: $20	Source10/15/2026

Performance

Shared benchmarks

Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.

Capability profile from matched benchmarks

Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.

Not enough directly matched categories for a reliable radar

Only 0 of at least 5 categories have comparable, direct model measurements. The benchmark tables below show the available evidence without filling missing axes.

Claude Haiku 5.5Muse Wonder

BioMysteryBenchOverall. Higher is better. Test setup not documented as identical

Claude Haiku 5.570.37 %

Muse Wonder67.037 %

Code MigrationOverall. Higher is better. Test setup not documented as identical

Claude Haiku 5.544.568 %

Muse Wonder62.552 %

CyberBench v1.1Overall. Higher is better. Test setup not documented as identical

Claude Haiku 5.575.476 %

Muse Wonder80.357 %

EMBOverall. Higher is better. Test setup not documented as identical

Claude Haiku 5.559.015 %

Muse Wonder67.084 %

Finance Agent (v2)Overall. Higher is better. Test setup not documented as identical

Claude Haiku 5.554.138 %

Muse Wonder56.637 %

Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. Test setup not documented as identical

Claude Haiku 5.51.25 %

Muse Wonder17.083 %

IOIOverall. Higher is better. Test setup not documented as identical

Claude Haiku 5.547.278 %

Muse Wonder66.944 %

Legal Research BenchOverall · All-pass. Higher is better. Test setup not documented as identical

Claude Haiku 5.543.269 %

Muse Wonder50.481 %

MysteryMechanismOverall. Higher is better. Test setup not documented as identical

Claude Haiku 5.535.135 %

Muse Wonder27.477 %

ProofBenchOverall. Higher is better. Test setup not documented as identical

Claude Haiku 5.589 %

Muse Wonder84 %

Public Benefits Bench v1.1Overall. Higher is better. Test setup not documented as identical

Claude Haiku 5.563.194 %

Muse Wonder70.23 %

SWE-bench MultimodalOverall. Higher is better. Test setup not documented as identical

Claude Haiku 5.543.958 %

Muse Wonder45.417 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Haiku 5.5 and Muse Wonder
Benchmark and task	Claude Haiku 5.5	Muse Wonder	Source
BioMysteryBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Harness: Terminus 2, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Harness: Terminus 2, Temperature: 1, Output limit: 131,072 tokens	Higher measured value70.37 %	67.037 %	Vals AI Source details Data as of: 10/12/2026
Code MigrationOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	44.568 %	Higher measured value62.552 %	Vals AI Source details Data as of: 10/12/2026
CyberBench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	75.476 %	Higher measured value80.357 %	Vals AI Source details Data as of: 10/12/2026
EMBOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	59.015 %	Higher measured value67.084 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	54.138 %	Higher measured value56.637 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	1.25 %	Higher measured value17.083 %	Vals AI Source details Data as of: 10/12/2026
IOIOverall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	47.278 %	Higher measured value66.944 %	Vals AI Source details Data as of: 10/14/2026
Legal Research BenchOverall · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	43.269 %	Higher measured value50.481 %	Vals AI Source details Data as of: 10/12/2026
MysteryMechanismOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	Higher measured value35.135 %	27.477 %	Vals AI Source details Data as of: 10/12/2026
ProofBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	Higher measured value89 %	84 %	Vals AI Source details Data as of: 10/12/2026
Public Benefits Bench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	63.194 %	Higher measured value70.23 %	Vals AI Source details Data as of: 10/12/2026
SWE-bench MultimodalOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	43.958 %	Higher measured value45.417 %	Vals AI Source details Data as of: 10/13/2026
Tax Agent BenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	31.922 %	Higher measured value36.269 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 4.0Overall Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	36.364 %	Higher measured value49.495 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceOverall Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Harness: Mini-SWE-agent, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 131,072 tokens	10 %	Higher measured value22.857 %	Vals AI Source details Data as of: 10/14/2026
Vals IndexOverall Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: weighted index scoreScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	54.435 %	Higher measured value61.062 %	Vals AI Source details Data as of: 10/13/2026
Vibe Code Bench 1-100Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.0Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Harness: OpenHands, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Harness: OpenHands, Temperature: 1, Output limit: 131,072 tokens	20.406 %	Higher measured value26.55 %	Vals AI Source details Data as of: 10/14/2026
Vibe Code Bench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Harness: OpenHands, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Harness: OpenHands, Temperature: 1, Output limit: 131,072 tokens	Higher measured value90.444 %	83.089 %	Vals AI Source details Data as of: 10/12/2026
BioMysteryBenchHard Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Harness: Terminus 2, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Harness: Terminus 2, Temperature: 1, Output limit: 131,072 tokens	No direct winner29.412 %	No direct winner29.412 %	Vals AI Source details Data as of: 10/12/2026
Code MigrationCLI Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	36.091 %	Higher measured value60.07 %	Vals AI Source details Data as of: 10/12/2026
CyberBench v1.1Patch Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	Higher measured value89.286 %	85.714 %	Vals AI Source details Data as of: 10/12/2026
EMBComps Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	77.925 %	Higher measured value79.488 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Adjustments Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	49.557 %	Higher measured value52.67 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	81.944 %	Higher measured value93.841 %	Vals AI Source details Data as of: 10/12/2026
IOIIOI 2024 Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	Higher measured value67.667 %	66.833 %	Vals AI Source details Data as of: 10/14/2026
Legal Research BenchAdministrative / Regulatory · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	50 %	Higher measured value63.636 %	Vals AI Source details Data as of: 10/12/2026
SWE-bench Multimodalbpmn-js Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	64.151 %	Higher measured value67.925 %	Vals AI Source details Data as of: 10/13/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	6.667 %	Higher measured value20 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 4.0Hardware Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	20 %	Higher measured value46.667 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceEarth Sciences Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Harness: Mini-SWE-agent, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 131,072 tokens	0 %	Higher measured value50 %	Vals AI Source details Data as of: 10/14/2026
Vals IndexCode Migration Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	45.921 %	Higher measured value62.009 %	Vals AI Source details Data as of: 10/13/2026
BioMysteryBenchHuman-solvable Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Harness: Terminus 2, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Harness: Terminus 2, Temperature: 1, Output limit: 131,072 tokens	Higher measured value79.909 %	75.799 %	Vals AI Source details Data as of: 10/12/2026
Code MigrationCOBOL Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	No direct winner70 %	No direct winner70 %	Vals AI Source details Data as of: 10/12/2026
CyberBench v1.1PoC Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	61.667 %	Higher measured value75 %	Vals AI Source details Data as of: 10/12/2026
EMBDataroom Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	Higher measured value85.482 %	79.232 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)All-Pass Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	42.874 %	Higher measured value45.936 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	0 %	Higher measured value20 %	Vals AI Source details Data as of: 10/12/2026
IOIIOI 2025 Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	31.333 %	Higher measured value75.5 %	Vals AI Source details Data as of: 10/14/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	88.676 %	Higher measured value90.571 %	Vals AI Source details Data as of: 10/12/2026
SWE-bench MultimodalCarbon Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	24.06 %	Higher measured value27.068 %	Vals AI Source details Data as of: 10/13/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	54.091 %	Higher measured value71.362 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 4.0Media Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	25 %	Higher measured value33.333 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceEngineering Sciences Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Harness: Mini-SWE-agent, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 131,072 tokens	No direct winner0 %	No direct winner0 %	Vals AI Source details Data as of: 10/14/2026
Vals IndexEMB Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	59.015 %	Higher measured value67.084 %	Vals AI Source details Data as of: 10/13/2026
Code MigrationCode Quality Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: mean reviewer code-quality ratingScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	Higher measured value4.825 / 5	4.061 / 5	Vals AI Source details Data as of: 10/12/2026
EMBDCF Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	Higher measured value55.108 %	51.035 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Comparables Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	45.325 %	Higher measured value47.933 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkArbitration International Dispute Resolution · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	48.746 %	Higher measured value92.473 %	Vals AI Source details Data as of: 10/12/2026
IOIIOI 2026 Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	42.833 %	Higher measured value58.5 %	Vals AI Source details Data as of: 10/14/2026
Legal Research BenchBusiness & Commercial · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	44.186 %	Higher measured value48.837 %	Vals AI Source details Data as of: 10/12/2026
SWE-bench MultimodalESLint Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	Higher measured value63.636 %	54.545 %	Vals AI Source details Data as of: 10/13/2026
Tax Agent BenchCurrent & Temporal Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	36.667 %	Higher measured value50 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 4.0ML Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	Higher measured value63.636 %	45.455 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceLife Sciences Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Harness: Mini-SWE-agent, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 131,072 tokens	15.789 %	Higher measured value21.053 %	Vals AI Source details Data as of: 10/14/2026
Vals IndexFinance Agent v2 Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	54.138 %	Higher measured value56.637 %	Vals AI Source details Data as of: 10/13/2026
EMBLBO Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	28.155 %	Higher measured value60.69 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Disclosure Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	64.256 %	Higher measured value67.252 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkArbitration International Dispute Resolution · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	No direct winner0 %	No direct winner0 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchBusiness & Commercial · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	Higher measured value87.024 %	86.88 %	Vals AI Source details Data as of: 10/12/2026
SWE-bench MultimodalFusion Next Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	33.333 %	Higher measured value38.889 %	Vals AI Source details Data as of: 10/13/2026
Tax Agent BenchCurrent & Temporal Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	56.197 %	Higher measured value77.655 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 4.0Operations Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	18.519 %	Higher measured value40.741 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceMathematical Sciences Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterClaude Haiku 5.5: Compute: max, Harness: Mini-SWE-agent, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 131,072 tokens	11.765 %	Higher measured value23.529 %	Vals AI Source details Data as of: 10/14/2026
Vals IndexHLAB Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterClaude Haiku 5.5: Compute: max, Output limit: 128,000 tokens Muse Wonder: Reasoning: max, Temperature: 1, Output limit: 131,072 tokens	1.25 %	Higher measured value17.083 %	Vals AI Source details Data as of: 10/13/2026
Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

There is no shared test round for this selection. Results from different rounds are not mixed.

How to read this comparison

Winning one benchmark is not an overall verdict

Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.

The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.

Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.

More matchups

Compare Claude Haiku 5.5 and Muse Wonder with other leading models using the same data and benchmark logic.

View the complete LLM comparison