Skip to main content

Head-to-head comparison

Claude Mythos 5 vs. Gemini 3.1 Pro Preview

Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.

1

shared result series

1

distinct benchmarks

2026-08-02

latest retrieval

Change model selection

Specifications and cost

General specifications and standard API pricing

Undisclosed parameter counts and knowledge cutoffs stay marked as unavailable. The table shows direct standard token pricing, including documented context tiers. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

Specifications and API pricing for Claude Mythos 5 and Gemini 3.1 Pro Preview
AttributeClaude Mythos 5Gemini 3.1 Pro Preview
ProviderAnthropicGoogle
ReleasedJun 9, 2026Feb 19, 2026
AvailabilityLimited accessPreview
Model typeProprietaryProprietary
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window1,000,000 tokens1,048,576 tokens
Knowledge cutoffJanuary 2026Not published
Technical sourcesModel, Context, Knowledge cutoffModel
API pricing per 1M tokens
API input$10$2 ≤200K / $4 >200K
API output$50$12 ≤200K / $18 >200K
Cache read$1$0.2 ≤200K / $0.4 >200K
Cache write (5 min.)$12.5Not listed
Cache write (1 hr.)$20Not listed
Price verified07/30/2026Source07/30/2026Source
Claude Mythos 5Gemini 3.1 Pro Preview
API inputUSD per 1M tokens, base tier
Claude Mythos 5$10
Gemini 3.1 Pro Preview$2Lower price
API outputUSD per 1M tokens, base tier
Claude Mythos 5$50
Gemini 3.1 Pro Preview$12Lower price
Cache readUSD per 1M tokens, base tier
Claude Mythos 5$1
Gemini 3.1 Pro Preview$0.2Lower price

Performance

Shared benchmarks

Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.

1 shared result series
Claude Mythos 5Gemini 3.1 Pro Preview
BrowseCompOverall. Higher is better. No documented setup difference
Claude Mythos 588 %Winner
Gemini 3.1 Pro Preview85.9 %
Benchmark scores for Claude Mythos 5 and Gemini 3.1 Pro Preview
Benchmark and taskClaude Mythos 5Gemini 3.1 Pro PreviewComparabilitySource
BrowseCompOverall
88 %Winner
Editorial selection from the vendor table, not a complete extract of the comparison cohort.
85.9 %
Editorial selection from the vendor table, not a complete extract of the comparison cohort.
1,266 tasksaccuracyHigher is betterCohort: browsecomp-openai-gpt-5-6-tableNo documented setup differenceWinner: Claude Mythos 5Claude Mythos 5: No further settings disclosed
Gemini 3.1 Pro Preview: No further settings disclosed
Cross-vendor comparison table with browsing tools. Exact agent systems differ.
OpenAIType: Vendor-reportedLeaderboard updated: 2026-07-09Import ID: curated-openai-2026-08-02-55280172a0ed / curated-openai-2026-08-02-6b6010847c80Retrieved 2026-08-02

How to read this comparison

Winning one benchmark is not an overall verdict

Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.

Prices use official API rates per 1M tokens. Web subscriptions and cloud platform surcharges can differ.

Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.