Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

See the free Radar Brief
Superseded.Anthropic has newer models in this line:Claude Mythos 5.1

Claude Mythos 5

SupersededReleased Jun 9, 2026ProprietaryReasoning1M context

Released Jun 9, 2026 see all recent releases

Decision reading
Claude Mythos 5 is tracked, but not publicly ranked yet. The profile exposes 20 sourced benchmark rows and leaves unsupported fields blank until a published record exists.

Data as of September 4, 2026 · How the score is built

Strongest published evidence

Published rows are visible, but no category has enough eligible evidence for a comparative rank.

Validate before choosing

20 published rows leave some tracked benchmark slots empty. Independent runtime speed has not been measured.

Decision snapshot

Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.

Capability

Unranked

field median 58.1

Not eligible for a public rank

Price

$10input / $50 output

input median $1

cached $1 · batch + cache $0.50 · blended $30

Speed

Not measured

field median 92 tok/s

Time to first token not measured

Context

1Mtokens

field median 256,000

Maximum output length is tracked separately

How much of this is verified

Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.

  1. Agentic4/4 verified
  2. Coding3/3 verified
  3. ReasoningNot measured
  4. Knowledge3/3 verified
  5. Math1/1 verified
  6. Multilingual1/1 verified
  7. Multimodal3/3 verified
  8. Inst. FollowingNot measured
Verified sourceProvisionalNot measured

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

API model ID
claude-mythos-5Anthropic model overview
Context window
1MAnthropic model overview
Maximum output
Not sourced yet
Knowledge cutoff
Not sourced yet
Input modalities
text, imageAnthropic model overview
Output modalities
textAnthropic model overview
Parameters
Not disclosed by the provider
Availability
Claude APIAnthropic model overview
Cloud regions
Not tracked yet
Lifecycle
limited accessAnthropic model overview
API capabilities
Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching
Published at $1 per million cached input tokensClaude API pricing
Self-host
Weights are not published
Rate limits
Not tracked yet

Category score record

Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank Not rankedWeight 22%4 benchmarksVerified93.2
CodingRank Not rankedWeight 20%3 benchmarksVerified87.5
ReasoningWeight 17%0 benchmarksNot measuredNot measured
KnowledgeRank Not rankedWeight 12%3 benchmarksVerified94.4
MathRank Not rankedWeight 5%1 benchmarkVerified97.6
MultilingualRank Not rankedWeight 7%1 benchmarkVerified92.7
MultimodalRank Not rankedWeight 12%3 benchmarksVerified85.1
Inst. FollowingWeight 5%0 benchmarksNot measuredNot measured

Benchmark ledger

Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.

Coding3 rows
Coding benchmark values, best verified comparison, weight, and source status
SWE-bench ProScore80.3%Versus best verified row

Best verified: Claude Fable 5.1 · 81.2%

Gap0.9 behindWeightWeighted 25%
SWE-bench VerifiedSoftware Engineering Benchmark VerifiedScore95.5%Versus best verified row

Best verified: Claude Opus 5 · 96%

Gap0.5 behindWeightWeighted 10%
Terminal-Bench 2.0Score88.0%Versus best verified row

Best verified: GPT-5.6 Sol · 91.9%

Gap3.9 behindWeightDisplay only
Agentic4 rows
Agentic benchmark values, best verified comparison, weight, and source status
Terminal-Bench 2.0Score88%Versus best verified row

Best verified: GPT-5.6 Sol · 91.9%

Gap3.9 behindWeightWeighted 30%
OSWorld-VerifiedScore85%Versus best verified row

Best verified: Qwen3.8 Max · 86.1%

Gap1.1 behindWeightWeighted 25%
BrowseCompScore88%Versus best verified row

Best verified: GPT-5.6 Sol · 92.2%

Gap4.2 behindWeightWeighted 25%
CyberGymScore83.8%Versus best verified row

Best verified: Fugu Cyber · 86.9%

Gap3.1 behindWeightDisplay only
Knowledge3 rows
Knowledge benchmark values, best verified comparison, weight, and source status
HLEHumanity's Last ExamScore64.5%Versus best verified row

Best verified: Claude Fable 5.1 · 65%

Gap0.5 behindWeightWeighted 35%
HLE w/o toolsHumanity's Last Exam without toolsScore59%Versus best verified row

Best verified: Claude Fable 5.1 · 60.9%

Gap1.9 behindWeightWeighted 10%
GPQAGraduate-Level Google-Proof Q&AScore94.1%Versus best verified row

Best verified: GPT-6 Astra · 96%

Gap1.9 behindWeightWeighted 7%
Math1 row
Math benchmark values, best verified comparison, weight, and source status
USAMO 2026United States of America Mathematical Olympiad 2026Score97.6%Versus best verified row

Best verified: Claude Mythos 5 · 97.6%

GapBest verifiedWeightWeighted 10%
Multilingual1 row
Multilingual benchmark values, best verified comparison, weight, and source status
SWE MultilingualSWE-bench MultilingualScore92.2%Versus best verified row

Best verified: Claude Mythos 5 · 92.2%

GapBest verifiedWeightDisplay only
Multimodal3 rows
Multimodal benchmark values, best verified comparison, weight, and source status
CharXivCharXiv ReasoningScore93.5%Versus best verified row

Best verified: Qwen3.8 Max · 93.5%

GapBest verifiedWeightWeighted 20%
SWE-bench MultimodalScore54.9%Versus best verified row

Best verified: Claude Mythos 5 · 54.9%

GapBest verifiedWeightDisplay only
CharXiv w/o toolsCharXiv Reasoning without toolsScore88.9%Versus best verified row

Best verified: Claude Mythos 5 · 88.9%

GapBest verifiedWeightDisplay only
External signals5 rows
External signals benchmark values, best verified comparison, weight, and source status
ExploitBenchExploitBench v8-benchScore78%Versus best verified row

Best verified: GPT-6 Astra · 100%

Gap22 behindWeightDisplay only
Firefox 147 exploitsFirefox 147 Working Exploit RateScore88.4%Versus best verified row

Best verified: Claude Mythos 5 · 88.4%

GapBest verifiedWeightDisplay only
Anthropic OSS-Fuzz crashAnthropic OSS-Fuzz Any-Crash RateScore80.0%Versus best verified row

Best verified: Claude Mythos 5 · 80.0%

GapBest verifiedWeightDisplay only
Anthropic OSS-Fuzz write primitiveAnthropic OSS-Fuzz Write-Primitive-or-Higher RateScore32.4%Versus best verified row

Best verified: Claude Mythos 5 · 32.4%

GapBest verifiedWeightDisplay only
The Last Ones completionThe Last Ones Cyber Range Completion RateScore60%Versus best verified row

Best verified: GPT-5.6 Sol · 70%

Gap10 behindWeightDisplay only

Lineage

The sequence follows explicit supersedes links. A successor's displayed score stays at least 0.1 points above its predecessor; raw benchmark rows do not move. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

  1. Jun 9, 2026 · you are here

    Claude Mythos 5

    Not publicly ranked · $10 / $50

  2. Sep 1, 2026

    Claude Mythos 5.1

    Not publicly ranked · Price not listed

Restricted

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

We track Claude Mythos 5, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.

Claude Mythos 5 is a proprietary model with a 1M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.

Claude Mythos 5 is restricted to Glasswing partners and trusted-access programs. Claude Fable 5 is the same underlying model made generally available with additional safeguards for cybersecurity, biology, chemistry, distillation, and frontier-AI-development requests.

Updated from Anthropic's June 9, 2026 Claude Fable 5 and Claude Mythos 5 launch pages and system card. BenchLM maps exact Mythos 5 rows, including the system card's safeguards-off cybersecurity evaluations. Anthropic says Fable 5 and Mythos 5 are the same underlying model, but the published cyber results are for Mythos 5 with safeguards off and do not describe Fable 5 behavior. Mythos is a restricted-access profile, so BenchLM keeps it on model and comparison pages and in the cybersecurity comparison while excluding it from general ranking tables.

Claude Mythos 5 sits in the Claude Mythos family with Claude Mythos 5.1, Claude Mythos Preview. 20 of 422 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.

Radar

Claude Mythos 5 release history

Full release history

Radar confirmed these at the source. Already tracking Claude Mythos 5? See the free Radar Brief for what changes next.

Frequently asked questions

How does Claude Mythos 5 perform overall in AI benchmarks?

Claude Mythos 5 has 20 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.

Is Claude Mythos 5 good for knowledge and understanding?

Claude Mythos 5 has source-displayable benchmark coverage for knowledge and understanding, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Claude Mythos 5 good for coding and programming?

Claude Mythos 5 has source-displayable benchmark coverage for coding and programming, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Claude Mythos 5 good for mathematics?

Claude Mythos 5 has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Claude Mythos 5 good for agentic tool use and computer tasks?

Claude Mythos 5 has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Claude Mythos 5 good for multimodal and grounded tasks?

Claude Mythos 5 has source-displayable benchmark coverage for multimodal and grounded tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Claude Mythos 5 good for multilingual tasks?

Claude Mythos 5 has source-displayable benchmark coverage for multilingual tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Which sibling models are related to Claude Mythos 5?

Claude Mythos 5 belongs to the Claude Mythos family. Related tracked variants include Claude Mythos 5.1, Claude Mythos Preview. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.

Does Claude Mythos 5 have full benchmark coverage on BenchLM?

No. Claude Mythos 5 currently has 20 source-displayable rows across 422 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of Claude Mythos 5?

Claude Mythos 5 has a documented context window of 1M. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.

Compare Claude Mythos 5 with every tracked model410 comparisons

Last updated September 4, 2026. Runtime fields remain blank until a sourced snapshot exists.

Watch Claude Mythos 5 in the weekly brief

Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.

Read a sample issue

Join 2,000+ readers.