Capability
Unranked
field median 58.1
Not eligible for a public rank
Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.
See the free Radar BriefReleased Jun 9, 2026 — see all recent releases
Data as of September 4, 2026 · How the score is built
Share or export
Published rows are visible, but no category has enough eligible evidence for a comparative rank.
20 published rows leave some tracked benchmark slots empty. Independent runtime speed has not been measured.
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
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.
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank Not rankedWeight 22%4 benchmarksVerified | 93.2 | Not ranked | Not available | 22% | 4 benchmarks | Verified |
| CodingRank Not rankedWeight 20%3 benchmarksVerified | 87.5 | Not ranked | Not available | 20% | 3 benchmarks | Verified |
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | Not ranked | Not available | 17% | 0 benchmarks | Not measured |
| KnowledgeRank Not rankedWeight 12%3 benchmarksVerified | 94.4 | Not ranked | Not available | 12% | 3 benchmarks | Verified |
| MathRank Not rankedWeight 5%1 benchmarkVerified | 97.6 | Not ranked | Not available | 5% | 1 benchmark | Verified |
| MultilingualRank Not rankedWeight 7%1 benchmarkVerified | 92.7 | Not ranked | Not available | 7% | 1 benchmark | Verified |
| MultimodalRank Not rankedWeight 12%3 benchmarksVerified | 85.1 | Not ranked | Not available | 12% | 3 benchmarks | Verified |
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
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.
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE-bench Pro | Score80.3% | Versus best verified row Best verified: Claude Fable 5.1 · 81.2% | Gap0.9 behind | WeightWeighted 25% | |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score95.5% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap0.5 behind | WeightWeighted 10% | |
| Terminal-Bench 2.0 | Score88.0% | Versus best verified row Best verified: GPT-5.6 Sol · 91.9% | Gap3.9 behind | WeightDisplay only |
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 | Score88% | Versus best verified row Best verified: GPT-5.6 Sol · 91.9% | Gap3.9 behind | WeightWeighted 30% | |
| OSWorld-Verified | Score85% | Versus best verified row Best verified: Qwen3.8 Max · 86.1% | Gap1.1 behind | WeightWeighted 25% | |
| BrowseComp | Score88% | Versus best verified row Best verified: GPT-5.6 Sol · 92.2% | Gap4.2 behind | WeightWeighted 25% | |
| CyberGym | Score83.8% | Versus best verified row Best verified: Fugu Cyber · 86.9% | Gap3.1 behind | WeightDisplay only |
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HLEHumanity's Last Exam | Score64.5% | Versus best verified row Best verified: Claude Fable 5.1 · 65% | Gap0.5 behind | WeightWeighted 35% | |
| HLE w/o toolsHumanity's Last Exam without tools | Score59% | Versus best verified row Best verified: Claude Fable 5.1 · 60.9% | Gap1.9 behind | WeightWeighted 10% | |
| GPQAGraduate-Level Google-Proof Q&A | Score94.1% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap1.9 behind | WeightWeighted 7% |
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| USAMO 2026United States of America Mathematical Olympiad 2026 | Score97.6% | Versus best verified row Best verified: Claude Mythos 5 · 97.6% | GapBest verified | WeightWeighted 10% |
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE MultilingualSWE-bench Multilingual | Score92.2% | Versus best verified row Best verified: Claude Mythos 5 · 92.2% | GapBest verified | WeightDisplay only |
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| CharXivCharXiv Reasoning | Score93.5% | Versus best verified row Best verified: Qwen3.8 Max · 93.5% | GapBest verified | WeightWeighted 20% | |
| SWE-bench Multimodal | Score54.9% | Versus best verified row Best verified: Claude Mythos 5 · 54.9% | GapBest verified | WeightDisplay only | |
| CharXiv w/o toolsCharXiv Reasoning without tools | Score88.9% | Versus best verified row Best verified: Claude Mythos 5 · 88.9% | GapBest verified | WeightDisplay only |
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| ExploitBenchExploitBench v8-bench | Score78% | Versus best verified row Best verified: GPT-6 Astra · 100% | Gap22 behind | WeightDisplay only | |
| Firefox 147 exploitsFirefox 147 Working Exploit Rate | Score88.4% | Versus best verified row Best verified: Claude Mythos 5 · 88.4% | GapBest verified | WeightDisplay only | |
| Anthropic OSS-Fuzz crashAnthropic OSS-Fuzz Any-Crash Rate | Score80.0% | Versus best verified row Best verified: Claude Mythos 5 · 80.0% | GapBest verified | WeightDisplay only | |
| Anthropic OSS-Fuzz write primitiveAnthropic OSS-Fuzz Write-Primitive-or-Higher Rate | Score32.4% | Versus best verified row Best verified: Claude Mythos 5 · 32.4% | GapBest verified | WeightDisplay only | |
| The Last Ones completionThe Last Ones Cyber Range Completion Rate | Score60% | Versus best verified row Best verified: GPT-5.6 Sol · 70% | Gap10 behind | WeightDisplay only |
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.
Jun 9, 2026 · you are here
Claude Mythos 5Not publicly ranked · $10 / $50
Sep 1, 2026
Claude Mythos 5.1Not publicly ranked · Price not listed
Restricted
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.
Anthropic · Model release
Radar confirmed these at the source. Already tracking Claude Mythos 5? See the free Radar Brief for what changes next.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Related resources
Last updated September 4, 2026. Runtime fields remain blank until a sourced snapshot exists.
Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.
Read a sample issueJoin 2,000+ readers.