Skip to main content
Radar

Keep up with the models you depend on. Follow price changes, retirements, and API updates.Follow the models you depend on.

Follow model changes
Anthropic logo
Model A
Claude Mythos Preview

Anthropic

Evidence status unavailable

90% interval unavailable

Claude Mythos Preview vs GPT-5.5

Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

OpenAI logo
Model B
GPT-5.5

OpenAI

72.07/100

Supported · Public rank #10

90% interval 68.575.7

Decision reading

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.

2 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Share or export

Share on XLinkedInSocial cardCSVJSON

Which one for your work

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.

  • Chat turn cost

    1K fresh input + 500 output tokens

    GPT-5.5

    GPT-5.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    GPT-5.5

    GPT-5.5 has the lower estimated token cost for this stated workload. Claude Mythos Preview has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback

Show secondary and unsupported calls
  • Repository review cost

    50K fresh input + 3K output tokens

    GPT-5.5

    GPT-5.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Claude Mythos Preview is not ranked on the public lane for coding, so no winner is named for coding.

    Confidence: limited

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    Claude Mythos Preview is not ranked on the public lane for agentic, so no winner is named for agentic.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    Not enough matched evidence

    A complete context comparison is not sourced.

    Confidence: limited

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

Shared results
2
Claude Mythos Preview only
0
GPT-5.5 only
37
Like-for-like categories
0 / 8

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign 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.

Agentic

Not comparable
Claude Mythos Preview
Not ranked
GPT-5.5
61.0
Supported · #17/152
Basis
BenchAlign lane · 2 vs 14 public rows
Reading
Not comparable

Coding

Not comparable
Claude Mythos Preview
Not ranked
GPT-5.5
67.6
Supported · #7/151
Basis
BenchAlign lane · 0 vs 9 public rows
Reading
Not comparable

Reasoning

Not comparable
Claude Mythos Preview
Not ranked
GPT-5.5
64.0
#13/20
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Knowledge

Not comparable
Claude Mythos Preview
Not ranked
GPT-5.5
72.9
Supported · #7/183
Basis
BenchAlign lane · 0 vs 6 public rows
Reading
Not comparable

Math

Not comparable
Claude Mythos Preview
Not ranked
GPT-5.5
69.6
Unranked · 3 rankable rows
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Claude Mythos Preview
Not ranked
GPT-5.5
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Claude Mythos Preview
Not ranked
GPT-5.5
71.3
#19/48
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Claude Mythos Preview
Not ranked
GPT-5.5
93.2
#7/123
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

What each workload costs

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.

Chat turn

1K fresh input + 500 output tokens

Claude Mythos Preview
$0.0875
Fit state unavailable
GPT-5.5
$0.02
Fits in one request

GPT-5.5 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Mythos Preview
$1.63
Fit state unavailable
GPT-5.5
$0.34
Fits in one request

GPT-5.5 has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Claude Mythos Preview
$6.75
Fit state unavailable
Cached input priced at the published list-input rate
GPT-5.5
$0.5
Fits in one request

GPT-5.5 has the lower modeled cost

Claude Mythos Preview has no published cached-input rate, so cached tokens use its listed input rate.

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Claude Mythos Preview

GPT-5.5

$0.5 per 1M cached input tokens

OpenAI pricing

Documented inputs

Claude Mythos Preview

Not sourced

GPT-5.5

Not sourced

Documented outputs

Claude Mythos Preview

Not sourced

GPT-5.5

Not sourced

Provider availability

Claude Mythos Preview

Limited Access · Project Glasswing participants

Anthropic Project Glasswing

GPT-5.5

Not sourced

Reasoning profile

Claude Mythos Preview

Reasoning

GPT-5.5

Reasoning

Weight access

Claude Mythos Preview

Proprietary

GPT-5.5

Proprietary

License

Claude Mythos Preview

Proprietary

GPT-5.5

Proprietary

Release date

Claude Mythos Preview

2026-04-07

GPT-5.5

2026-04-23

If you already use one of these models
Deployment change
The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
Workload cost
Repository review: $1.63 vs $0.34. Cache-heavy agent loop: $6.75 vs $0.5.
Context tradeoff
A complete documented context comparison is not available.

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence39 rows

Agentic

  • CyberGym

    Claude Mythos Preview83.1%
    Source
    GPT-5.581.8%
    Source

    Claude Mythos Preview leads this result

  • ExploitGym

    Shared source
    Claude Mythos Preview17.5%
    GPT-5.513.4%

    Claude Mythos Preview leads this result

  • Terminal-Bench 2.0

    Claude Mythos Preview
    GPT-5.582%
    Source

    Not directly comparable

  • BrowseComp

    Claude Mythos Preview
    GPT-5.584.4%
    Source

    Not directly comparable

  • OSWorld-Verified

    Claude Mythos Preview
    GPT-5.578.7%
    Source

    Not directly comparable

  • MCP Atlas

    Claude Mythos Preview
    GPT-5.575.3%
    Source

    Not directly comparable

  • Toolathlon

    Claude Mythos Preview
    GPT-5.555.6%
    Source

    Not directly comparable

  • τ²-bench results

    Claude Mythos Preview
    GPT-5.598%
    Source

    Not directly comparable

  • Gert Labs

    Claude Mythos Preview
    GPT-5.572.93%
    Source

    Not directly comparable

  • ResearchClawBench

    Claude Mythos Preview
    GPT-5.517.0%
    Source

    Not directly comparable

  • OSWorld 2.0

    Claude Mythos Preview
    GPT-5.513.0%
    Source

    Not directly comparable

  • JobBench

    Claude Mythos Preview
    GPT-5.542.7%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Claude Mythos Preview
    GPT-5.576.4%
    Source

    Not directly comparable

  • ApprenticeBench

    Claude Mythos Preview
    GPT-5.520%
    Source

    Not directly comparable

Coding

  • SWE-bench Pro

    Claude Mythos Preview
    GPT-5.558.6%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    Claude Mythos Preview
    GPT-5.582.0%
    Source

    Not directly comparable

  • Vibe Code Bench

    Claude Mythos Preview
    GPT-5.569.85%
    Source

    Not directly comparable

  • React Native Evals

    Claude Mythos Preview
    GPT-5.584.7%
    Source

    Not directly comparable

  • cursorBench31

    Claude Mythos Preview
    GPT-5.559.2%
    Source

    Not directly comparable

  • cursorBench32

    Claude Mythos Preview
    GPT-5.558.4%
    Source

    Not directly comparable

  • FrontierCode 1.1 Main

    Claude Mythos Preview
    GPT-5.543.0%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    Claude Mythos Preview
    GPT-5.585.3%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    Claude Mythos Preview
    GPT-5.582.6%
    Source

    Not directly comparable

Reasoning

  • MRCR v2 64K-128K

    Claude Mythos Preview
    GPT-5.583.1%
    Source

    Not directly comparable

  • MRCR v2 128K-256K

    Claude Mythos Preview
    GPT-5.587.5%
    Source

    Not directly comparable

  • ARC-AGI-2

    Claude Mythos Preview
    GPT-5.585%
    Source

    Not directly comparable

  • ARC-AGI-3

    Claude Mythos Preview
    GPT-5.50.4%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Claude Mythos Preview
    GPT-5.593.6%
    Source

    Not directly comparable

  • GPQA-D

    Claude Mythos Preview
    GPT-5.593.6%
    Source

    Not directly comparable

  • HLE

    Claude Mythos Preview
    GPT-5.552.2%
    Source

    Not directly comparable

  • HLE w/o tools

    Claude Mythos Preview
    GPT-5.541.4%
    Source

    Not directly comparable

  • GPQA Diamond (Vals)

    Claude Mythos Preview
    GPT-5.593.2%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    Claude Mythos Preview
    GPT-5.588.1%
    Source

    Not directly comparable

Math

  • FrontierMath (legacy)

    Claude Mythos Preview
    GPT-5.551.7%
    Source

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    Claude Mythos Preview
    GPT-5.551.700%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Claude Mythos Preview
    GPT-5.535.400%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    Claude Mythos Preview
    GPT-5.581.2%
    Source

    Not directly comparable

  • MMMU-Pro w/ Python

    Claude Mythos Preview
    GPT-5.583.2%
    Source

    Not directly comparable

  • OfficeQA Pro

    Claude Mythos Preview
    GPT-5.554.1%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Claude Mythos Preview or GPT-5.5?

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Claude Mythos Preview or GPT-5.5?

Claude Mythos Preview is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Claude Mythos Preview or GPT-5.5?

Claude Mythos Preview is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Claude Mythos Preview or GPT-5.5?

For the stated presets, chat costs $0.0875 on Claude Mythos Preview and $0.02 on GPT-5.5; repository review costs $1.63 and $0.34; the cache-heavy agent loop costs $6.75 and $0.5. Claude Mythos Preview has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Claude Mythos Preview or GPT-5.5?

A complete documented context-window comparison is not available.

Related comparisons

Last updated September 10, 2026

Watch Claude Mythos Preview vs GPT-5.5

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.