Coding
Like-for-like- Claude Mythos 5
- 89.7
- Claude Opus 5
- 89.5
- Weighted basis
- 2 vs 2 rows
- Reading
- Claude Mythos 5 leads
Claude Mythos 5 vs Claude Opus 5
Updated August 22, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Claude Mythos 5 has the higher public score estimate, 82.95 versus 82.72, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
5 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
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.
Coding work
Code generation, repair, and software-engineering tasks
Claude Mythos 5
Claude Mythos 5 leads on the same 2 weighted benchmark rows.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Claude Opus 5
Claude Opus 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
Claude Opus 5
Claude Opus 5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Claude Opus 5
Claude Opus 5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
10 Claude Mythos 5 only
5 Shared
58 Claude Opus 5 only
- Shared results
- 5
- Claude Mythos 5 only
- 10
- Claude Opus 5 only
- 58
- Like-for-like categories
- 1 / 8
2 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Agentic
Directional only- Claude Mythos 5
- 87.0
- Claude Opus 5
- 90.8
- Weighted basis
- 3 vs 1 rows
- Reading
- Directional only
Knowledge
Directional only- Claude Mythos 5
- 68.5
- Claude Opus 5
- 64.7
- Weighted basis
- 2 vs 1 rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Mythos 5
- Not measured
- Claude Opus 5
- 90.4
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Math
Not comparable- Claude Mythos 5
- 97.6
- Claude Opus 5
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Mythos 5
- Not measured
- Claude Opus 5
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Mythos 5
- 93.5
- Claude Opus 5
- 66.9
- Weighted basis
- 1 vs 1 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Mythos 5
- Not measured
- Claude Opus 5
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Claude Mythos 5 | Claude Opus 5 | Weighted basis | Reading |
|---|---|---|---|---|
| Coding | 89.7 | 89.5 | Like-for-like2 vs 2 rows | Claude Mythos 5 leads |
| Agentic | 87.0 | 90.8 | Directional only3 vs 1 rows | Directional only |
| Knowledge | 68.5 | 64.7 | Directional only2 vs 1 rows | Directional only |
| Reasoning | Not measured | 90.4 | Not comparable0 vs 1 rows | Not comparable |
| Math | 97.6 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | 93.5 | 66.9 | Not comparable1 vs 1 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
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.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
BrowseComp
Agentic
Claude Mythos 5: 88%Claude Opus 5: 90.8%Normalized gap 2.8Claude Mythos 5 source Claude Opus 5 sourceSWE-bench Pro
Coding
Claude Mythos 5: 80.3%Claude Opus 5: 79.2%Normalized gap 1.1Claude Mythos 5 source Claude Opus 5 sourceSWE-bench Verified
Coding
Claude Mythos 5: 95.5%Claude Opus 5: 96%Normalized gap 0.5Claude Mythos 5 source Claude Opus 5 sourceHLE
Knowledge
Claude Mythos 5: 64.5%Claude Opus 5: 64.7%Normalized gap 0.2Claude Mythos 5 source Claude Opus 5 source
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 5
- $0.035
- Fits in one request
- Claude Opus 5
- $0.0175
- Fits in one request
Claude Opus 5 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Mythos 5
- $0.65
- Fits in one request
- Claude Opus 5
- $0.325
- Fits in one request
Claude Opus 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 5
- $0.9
- Fits in one request
- Claude Opus 5
- $0.45
- Fits in one request
Claude Opus 5 has the lower modeled cost
Costs use the listed standard API rates.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Mythos 5Claude Opus 5
Context window
Maximum documented context; output-token limits may be lower.
Claude Mythos 5
Claude Opus 5
API model ID
Claude Mythos 5
claude-mythos-5
Anthropic model overviewClaude Opus 5
claude-opus-5
Anthropic model overviewCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Mythos 5
$1 per 1M cached input tokens
Claude API pricingClaude Opus 5
$0.5 per 1M cached input tokens
Claude API pricingDocumented inputs
Claude Mythos 5
text, image
Anthropic model overviewClaude Opus 5
text, image
Anthropic model overviewDocumented outputs
Claude Mythos 5
Claude Opus 5
Provider availability
Claude Mythos 5
Limited Access · Claude API
Anthropic model overviewClaude Opus 5
Generally Available · Claude API
Anthropic model overviewReasoning profile
Claude Mythos 5
Reasoning
Claude Opus 5
Reasoning
Weight access
Claude Mythos 5
Proprietary
Claude Opus 5
Proprietary
License
Claude Mythos 5
Proprietary
Claude Opus 5
Proprietary
Release date
Claude Mythos 5
2026-06-09
Claude Opus 5
2026-07-24
If you already use one of these models
- Deployment change
- Both entries list Anthropic as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- Claude Mythos 5 has the higher public score estimate, 82.95 versus 82.72, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.65 vs $0.325. Cache-heavy agent loop: $0.9 vs $0.45.
- Context tradeoff
- Both models list 1M.
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 evidence73 rows
Agentic
Terminal-Bench 2.0
Claude Mythos 588%SourceClaude Opus 5—Not directly comparable
OSWorld-Verified
Claude Mythos 585%SourceClaude Opus 5—Not directly comparable
BrowseComp
Claude Mythos 588%SourceClaude Opus 590.8%SourceClaude Opus 5 leads this result
CyberGym
Claude Mythos 583.8%SourceClaude Opus 5—Not directly comparable
Terminal-Bench 3.0
Claude Mythos 5—Claude Opus 542.7%SourceNot directly comparable
HLE w/ tools
Claude Mythos 5—Claude Opus 564.7%SourceNot directly comparable
DeepSearchQA
Claude Mythos 5—Claude Opus 595.0%SourceNot directly comparable
DRACO
Claude Mythos 5—Claude Opus 588.6%SourceNot directly comparable
BrowseComp (10-agent, prerelease)
Claude Mythos 5—Claude Opus 593.6%SourceNot directly comparable
OSWorld 2.0
Claude Mythos 5—Claude Opus 570.6%SourceNot directly comparable
MCP Atlas
Claude Mythos 5—Claude Opus 585.8%SourceNot directly comparable
MCP-Atlas claim coverage
Claude Mythos 5—Claude Opus 589.1%SourceNot directly comparable
LAB all-pass (Anthropic harness)
Claude Mythos 5—Claude Opus 523.58%SourceNot directly comparable
LAB criterion-pass (Anthropic harness)
Claude Mythos 5—Claude Opus 593.74%SourceNot directly comparable
LAB all-pass (Harvey held-out)
Claude Mythos 5—Claude Opus 511.7%SourceNot directly comparable
LAB criterion-pass (Harvey held-out)
Claude Mythos 5—Claude Opus 594.1%SourceNot directly comparable
Toolathlon-Verified
Claude Mythos 5—Claude Opus 580.6%SourceNot directly comparable
Toolathlon Verified Pass@3
Claude Mythos 5—Claude Opus 587.0%SourceNot directly comparable
Toolathlon Verified Pass³
Claude Mythos 5—Claude Opus 573.1%SourceNot directly comparable
Toolathlon Verified avg. turns
Claude Mythos 5—Claude Opus 523.5 turnsSourceNot directly comparable
AutomationBench
Claude Mythos 5—Claude Opus 526.0%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Mythos 595.5%SourceClaude Opus 596%SourceClaude Opus 5 leads this result
SWE-bench Pro
Claude Mythos 580.3%SourceClaude Opus 579.2%SourceClaude Mythos 5 leads this result
Terminal-Bench 2.0
Claude Mythos 588.0%SourceClaude Opus 5—Not directly comparable
SWE Multilingual
Claude Mythos 5—Claude Opus 589.5%SourceNot directly comparable
SWE Multimodal
Claude Mythos 5—Claude Opus 559.4%SourceNot directly comparable
deepSwe
Claude Mythos 5—Claude Opus 568.8%SourceNot directly comparable
FrontierCode 1.1 Main
Claude Mythos 5—Claude Opus 553.4%SourceNot directly comparable
FrontierCode 1.1 Extended
Claude Mythos 5—Claude Opus 563.6%SourceNot directly comparable
ProgramBench (episode 1)
Claude Mythos 5—Claude Opus 583.0%SourceNot directly comparable
ProgramBench
Claude Mythos 5—Claude Opus 593.0%SourceNot directly comparable
cursorBench32
Claude Mythos 5—Claude Opus 570.0%SourceNot directly comparable
VulcanBench v3
Claude Mythos 5—Claude Opus 587.0%SourceNot directly comparable
Reasoning
Knowledge
GPQA
Claude Mythos 594.1%SourceClaude Opus 5—Not directly comparable
HLE
Claude Mythos 564.5%SourceClaude Opus 564.7%SourceClaude Opus 5 leads this result
HLE w/o tools
Claude Mythos 559%SourceClaude Opus 556.3%SourceClaude Mythos 5 leads this result
HealthBench (raw)
Claude Mythos 5—Claude Opus 567.1%SourceNot directly comparable
HealthBench (length-adjusted)
Claude Mythos 5—Claude Opus 557.8%SourceNot directly comparable
HealthBench Professional
Claude Mythos 5—Claude Opus 559.8%SourceNot directly comparable
HealthBench Professional (raw)
Claude Mythos 5—Claude Opus 573.4%SourceNot directly comparable
BioMysteryBench (human-solvable)
Claude Mythos 5—Claude Opus 590.1%SourceNot directly comparable
BioMysteryBench (human-difficult)
Claude Mythos 5—Claude Opus 549.4%SourceNot directly comparable
SpatialBench Verified
Claude Mythos 5—Claude Opus 572.5%SourceNot directly comparable
SingleCellBench
Claude Mythos 5—Claude Opus 560.6%SourceNot directly comparable
ProteinGym Hard
Claude Mythos 5—Claude Opus 547.7%SourceNot directly comparable
Protein Design
Claude Mythos 5—Claude Opus 542.5%SourceNot directly comparable
Organic chemistry V2
Claude Mythos 5—Claude Opus 561.6%SourceNot directly comparable
Protocols (troubleshooting)
Claude Mythos 5—Claude Opus 561.1%SourceNot directly comparable
Protocols (understanding)
Claude Mythos 5—Claude Opus 578.4%SourceNot directly comparable
Math
USAMO 2026
Claude Mythos 597.6%SourceClaude Opus 5—Not directly comparable
IMO 2026
Claude Mythos 5—Claude Opus 542/42SourceNot directly comparable
RiemannBench (no tools)
Claude Mythos 5—Claude Opus 560.0%SourceNot directly comparable
RiemannBench (tools)
Claude Mythos 5—Claude Opus 579.0%SourceNot directly comparable
ArXivMath Jun. 2026 (no tools)
Claude Mythos 5—Claude Opus 590.8%SourceNot directly comparable
ArXivMath Jun. 2026 (tools)
Claude Mythos 5—Claude Opus 591.3%SourceNot directly comparable
Multilingual
Multimodal
SWE-bench Multimodal
Claude Mythos 554.9%SourceClaude Opus 5—Not directly comparable
CharXiv
Claude Mythos 593.5%SourceClaude Opus 5—Not directly comparable
CharXiv w/o tools
Claude Mythos 588.9%SourceClaude Opus 5—Not directly comparable
Chartography (no tools)
Claude Mythos 5—Claude Opus 529.6%SourceNot directly comparable
Chartography (tools)
Claude Mythos 5—Claude Opus 583.0%SourceNot directly comparable
BenchCAD Vision2Code (no tools)
Claude Mythos 5—Claude Opus 50.366SourceNot directly comparable
BenchCAD Vision2Code (tools)
Claude Mythos 5—Claude Opus 50.821SourceNot directly comparable
GDP.pdf (no tools)
Claude Mythos 5—Claude Opus 583.4%SourceNot directly comparable
GDP.pdf (tools)
Claude Mythos 5—Claude Opus 585.5%SourceNot directly comparable
OfficeQA
Claude Mythos 5—Claude Opus 578.1%SourceNot directly comparable
OfficeQA Pro
Claude Mythos 5—Claude Opus 566.9%SourceNot directly comparable
Frequently asked questions
Which is better, Claude Mythos 5 or Claude Opus 5?
Claude Mythos 5 has the higher public score estimate, 82.95 versus 82.72, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Claude Mythos 5 or Claude Opus 5?
Claude Mythos 5 leads the like-for-like coding comparison across 2 shared weighted benchmark rows.
Which is better for agentic tasks, Claude Mythos 5 or Claude Opus 5?
The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Claude Mythos 5 or Claude Opus 5?
For the stated presets, chat costs $0.035 on Claude Mythos 5 and $0.0175 on Claude Opus 5; repository review costs $0.65 and $0.325; the cache-heavy agent loop costs $0.9 and $0.45. Costs use the listed standard API rates.
Which has the larger context window, Claude Mythos 5 or Claude Opus 5?
Both models list the same context window, 1M.
Related comparisons
Last updated August 22, 2026
Watch Claude Mythos 5 vs Claude Opus 5
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.