Sign Up

Decision support

Claude Haiku 5.5 vs Muse Ember

Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.

ModelsHardware
Claude Haiku 5.5

Anthropic

Sources:models.devOpenRouter

Muse Ember

Meta

Sources:models.devOpenRouter

Benchmark results

Head to head on 2 benchmarks both models report · 2 ties

  • Claude Haiku 5.50leads
  • Muse Ember0leads

  • Arena Text

    Arena rating · Higher is better

    • Claude Haiku 5.5
      1422
      Arena #131CI 1416 to 1429
    • Muse Ember
      Not reported
    Runs and sources
    Claude Haiku 5.5
    • high142295% CI 1416 to 1429 · 13,239 votes
    Muse Ember

    Not reported

    Source:Arena Text leaderboard, 2026-11-09

  • Arena WebDev

    Arena rating · Higher is better

    Tie, within 95% CI
    • Claude Haiku 5.5
      1594
      Arena #38CI 1585 to 1602
    • Muse Ember
      1609
      Arena #36CI 1592 to 1625
    Runs and sources
    Claude Haiku 5.5
    • high159495% CI 1585 to 1602 · 6,549 votes
    Muse Ember
    • max160995% CI 1592 to 1625 · 1,337 votes
    Source:Arena WebDev leaderboard, 2026-11-10

  • Agent Arena

    IPS score · Higher is better

    Tie, within 95% CI
    • Claude Haiku 5.5
      +0.005
      Arena #29CI -0.006 to +0.015
    • Muse Ember
      +0.017
      Arena #25CI -0.006 to +0.039
    Runs and sources
    Claude Haiku 5.5
    • high+0.00595% CI -0.006 to +0.015 · 4,460,773 observations
    Muse Ember
    • max+0.01795% CI -0.006 to +0.039 · 186,844 observations
    Source:Agent Arena leaderboard, 2026-11-11

  • ARC-AGI-2

    Best published score · Higher is better

    • Claude Haiku 5.5
      61.3%
      #33 of 85
    • Muse Ember
      Not reported
    Runs and sources
    Claude Haiku 5.5
    • low2.8%
    • medium9.4%
    • high30.7%
    • xhigh61.3%
    Muse Ember

    Not reported

    Source:External evaluation via Epoch AIOriginal-source terms apply

  • FrontierMath-Tier-4-v2-Private

    Best published score · Higher is better

    • Claude Haiku 5.5
      46.3%
      #23 of 72
    • Muse Ember
      Not reported
    Runs and sources
    Claude Haiku 5.5
    • max46.3%
    Muse Ember

    Not reported

    Source:Epoch AI evaluation

  • FrontierMath-Tiers-1-3-v2-Private

    Best published score · Higher is better

    • Claude Haiku 5.5
      75.1%
      #22 of 87
    • Muse Ember
      Not reported
    Runs and sources
    Claude Haiku 5.5
    • max75.1%
    Muse Ember

    Not reported

    Source:Epoch AI evaluation

  • GPQA diamond

    Best published score · Higher is better

    • Claude Haiku 5.5
      89.6%
      #47 of 161
    • Muse Ember
      Not reported
    Runs and sources
    Claude Haiku 5.5
    • max89.6%
    Muse Ember

    Not reported

    Source:Epoch AI evaluation

  • Humanity's Last Exam

    Best published score · Higher is better

    • Claude Haiku 5.5
      30.1%
      #12 of 34
    • Muse Ember
      Not reported
    Runs and sources
    Claude Haiku 5.5
    • unknown30.1%
    Muse Ember

    Not reported

    Source:External evaluation via Epoch AIOriginal-source terms apply

  • OTIS Mock AIME 2024-2025

    Best published score · Higher is better

    • Claude Haiku 5.5
      98.9%
      #19 of 158
    • Muse Ember
      Not reported
    Runs and sources
    Claude Haiku 5.5
    • high97.2%
    • xhigh98.9%
    Muse Ember

    Not reported

    Source:Epoch AI evaluation

  • SimpleQA Verified

    Best published score · Higher is better

    • Claude Haiku 5.5
      23.8%
      #72 of 87
    • Muse Ember
      Not reported
    Runs and sources
    Claude Haiku 5.5
    • max23.8%
    Muse Ember

    Not reported

    Source:Epoch AI evaluation

Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.

Original-source terms apply to evaluations credited to their original publishers.

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.

Model specifications

Release date
October 7, 2026
November 9, 2026
Context window
1M
1M
Native context
—
—
Max output tokens
128,000
943,718
Knowledge cutoff
2026-06
—
Open weights
Closed
Closed
Parameter count
—
—

API pricing · USD per 1M tokens

Input
$0.10
$0.10
Output
$0.50
$0.50
Cached input
$0.01
$0.004
Cache write
$0.125
$0.125

Capabilities and modalities

Input modalities
text, image, file
text, image, video, file, audio
Output modalities
text
text
Tool calling
Supported
Supported
Reasoning option
Supported
Supported
Supported options
include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, stop, structured_outputs, tool_choice, tools, verbosity
include_reasoning, max_tokens, reasoning, reasoning_effort, repetition_penalty, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_k, top_p
Capabilities
—
—

Architecture and availability

Architecture
—
—
Model families
—
—
Tokenizer
Claude
Other
Instruction format
—
—
License
—
—
Providers
5
2
Provider endpoints
20
2
Ollama variants
0
0
Metadata source
ai-research
ai-research

A dash means the field is not reported. Provider-specific performance and pricing may differ.

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.