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
BenchLM
Anthropic logo
Model A
Claude Opus 5

Anthropic

80.66/100

Supported · Public rank #4

90% interval 78.3–83.0

Claude Opus 5 vs o3-mini

Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

OpenAI logo
Model B
o3-mini

OpenAI

48.06/100

Supported · Public rank #153

90% interval 37.7–58.4

Decision reading

Claude Opus 5 has the higher public score, 80.66 versus 48.06, and the 90% score intervals do not overlap.

1 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.

  • Coding work

    Code generation, repair, and software-engineering tasks

    Claude Opus 5

    Claude Opus 5 leads on the public coding lane, 75.6 to 40.6, with Supported evidence for both models and non-overlapping 90% intervals.

    Confidence: stronger

  • Long documents

    Prompts that approach the documented context limit

    Claude Opus 5

    Claude Opus 5 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    o3-mini

    o3-mini 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

    o3-mini

    o3-mini 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

    O3-mini is not ranked on the public lane for agentic, so no winner is named for agentic.

    Confidence: limited

  • Cache-heavy agent loop cost

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

    Not enough matched evidence

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. o3-mini does not fit this workload in one request. o3-mini has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback

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
1
Claude Opus 5 only
72
o3-mini only
4
Like-for-like categories
2 / 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.

Coding

Like-for-like
Claude Opus 5
75.6
Supported · #3/183
o3-mini
40.6
Supported · #140/183
Basis
BenchAlign lane · 16 vs 1 public rows
Reading
Claude Opus 5 leads

Knowledge

Like-for-like
Claude Opus 5
82.1
Supported · #3/181
o3-mini
42.3
Supported · #127/181
Basis
BenchAlign lane · 19 vs 2 public rows
Reading
Claude Opus 5 leads

Agentic

Not comparable
Claude Opus 5
77.4
Supported · #2/151
o3-mini
Not ranked
Basis
BenchAlign lane · 19 vs 0 public rows
Reading
Not comparable

Reasoning

Not comparable
Claude Opus 5
75.6
#13/22
o3-mini
Not ranked
Basis
Provisional lane · 2 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Claude Opus 5
Not ranked
o3-mini
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Claude Opus 5
Not ranked
o3-mini
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Claude Opus 5
88.7
#2/48
o3-mini
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Claude Opus 5
Not ranked
o3-mini
Not ranked
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.

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.

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 Opus 5
$0.0175
Fits in one request
o3-mini
$0.0033
Fits in one request

o3-mini has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Opus 5
$0.325
Fits in one request
o3-mini
$0.0682
Fits in one request

o3-mini 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 Opus 5
$0.45
Fits in one request
o3-mini
$0.286
Does not fit in one request
Cached input priced at the published list-input rate

o3-mini does not fit this workload in one request. o3-mini 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.

Context window

Maximum documented context; output-token limits may be lower.

o3-mini

200K

Cached-input rate

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

Claude Opus 5

$0.5 per 1M cached input tokens

Claude API pricing

o3-mini

Not published

Reasoning profile

Claude Opus 5

Reasoning

o3-mini

Reasoning

Weight access

Claude Opus 5

Proprietary

o3-mini

Proprietary

License

Claude Opus 5

Proprietary

o3-mini

Proprietary

Release date

Claude Opus 5

2026-07-24

o3-mini

2025-01-31

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
Claude Opus 5 has the higher public score, 80.66 versus 48.06, and the 90% score intervals do not overlap.
Workload cost
Repository review: $0.325 vs $0.0682. Cache-heavy agent loop: $0.45 vs $0.286.
Context tradeoff
Claude Opus 5 has the larger documented window (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 evidence77 rows

Agentic

  • Terminal-Bench 3.0

    Claude Opus 542.7%
    Source
    o3-mini—

    Not directly comparable

  • BrowseComp

    Claude Opus 590.8%
    Source
    o3-mini—

    Not directly comparable

  • HLE w/ tools

    Claude Opus 564.7%
    Source
    o3-mini—

    Not directly comparable

  • DeepSearchQA

    Claude Opus 595.0%
    Source
    o3-mini—

    Not directly comparable

  • DRACO

    Claude Opus 588.6%
    Source
    o3-mini—

    Not directly comparable

  • BrowseComp (10-agent, prerelease)

    Claude Opus 593.6%
    Source
    o3-mini—

    Not directly comparable

  • OSWorld 2.0

    Claude Opus 570.6%
    Source
    o3-mini—

    Not directly comparable

  • MCP Atlas

    Claude Opus 585.8%
    Source
    o3-mini—

    Not directly comparable

  • MCP-Atlas claim coverage

    Claude Opus 589.1%
    Source
    o3-mini—

    Not directly comparable

  • LAB all-pass (Anthropic harness)

    Claude Opus 523.58%
    Source
    o3-mini—

    Not directly comparable

  • LAB criterion-pass (Anthropic harness)

    Claude Opus 593.74%
    Source
    o3-mini—

    Not directly comparable

  • LAB all-pass (Harvey held-out)

    Claude Opus 511.7%
    Source
    o3-mini—

    Not directly comparable

  • LAB criterion-pass (Harvey held-out)

    Claude Opus 594.1%
    Source
    o3-mini—

    Not directly comparable

  • Toolathlon-Verified

    Claude Opus 580.6%
    Source
    o3-mini—

    Not directly comparable

  • Toolathlon Verified Pass@3

    Claude Opus 587.0%
    Source
    o3-mini—

    Not directly comparable

  • Toolathlon Verified Pass³

    Claude Opus 573.1%
    Source
    o3-mini—

    Not directly comparable

  • Toolathlon Verified avg. turns

    Claude Opus 523.5 turns
    Source
    o3-mini—

    Not directly comparable

  • AutomationBench

    Claude Opus 526.0%
    Source
    o3-mini—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Claude Opus 584.6%
    Source
    o3-mini—

    Not directly comparable

Coding

  • Bug Hunt Bench

    Claude Opus 527 fixes
    Source
    o3-mini—

    Not directly comparable

  • SWE-bench Verified

    Claude Opus 596%
    Source
    o3-mini49.3%
    Source

    Claude Opus 5 leads this result

  • SWE-bench Pro

    Claude Opus 579.2%
    Source
    o3-mini—

    Not directly comparable

  • SWE Multilingual

    Claude Opus 589.5%
    Source
    o3-mini—

    Not directly comparable

  • SWE Multimodal

    Claude Opus 559.4%
    Source
    o3-mini—

    Not directly comparable

  • deepSwe

    Claude Opus 568.8%
    Source
    o3-mini—

    Not directly comparable

  • FrontierCode 1.1 Main

    Claude Opus 553.4%
    Source
    o3-mini—

    Not directly comparable

  • FrontierCode 1.1 Extended

    Claude Opus 563.6%
    Source
    o3-mini—

    Not directly comparable

  • FrontierSWE v2

    Claude Opus 552.0%
    Source
    o3-mini—

    Not directly comparable

  • ProgramBench (episode 1)

    Claude Opus 583.0%
    Source
    o3-mini—

    Not directly comparable

  • ProgramBench

    Claude Opus 593.0%
    Source
    o3-mini—

    Not directly comparable

  • cursorBench32

    Claude Opus 570.0%
    Source
    o3-mini—

    Not directly comparable

  • VulcanBench v3

    Claude Opus 587.0%
    Source
    o3-mini—

    Not directly comparable

  • VulcanBench CII v1

    Claude Opus 596.4%
    Source
    o3-mini—

    Not directly comparable

  • LiveCodeBench (Vals)

    Claude Opus 589.0%
    Source
    o3-mini—

    Not directly comparable

  • SWE-bench (Vals)

    Claude Opus 597.0%
    Source
    o3-mini—

    Not directly comparable

Reasoning

  • ARC-AGI-1

    Claude Opus 597.50%
    Source
    o3-mini—

    Not directly comparable

  • ARC-AGI-2

    Claude Opus 590.4%
    Source
    o3-mini—

    Not directly comparable

  • ARC-AGI-3

    Claude Opus 530.2%
    Source
    o3-mini—

    Not directly comparable

Knowledge

  • HLE

    Claude Opus 564.7%
    Source
    o3-mini—

    Not directly comparable

  • HLE w/o tools

    Claude Opus 556.3%
    Source
    o3-mini—

    Not directly comparable

  • HLE-Verified

    Claude Opus 554.4%
    Source
    o3-mini—

    Not directly comparable

  • LABBench2

    Claude Opus 584.2%
    Source
    o3-mini—

    Not directly comparable

  • HealthBench (raw)

    Claude Opus 567.1%
    Source
    o3-mini—

    Not directly comparable

  • HealthBench (length-adjusted)

    Claude Opus 557.8%
    Source
    o3-mini—

    Not directly comparable

  • HealthBench Professional

    Claude Opus 559.8%
    Source
    o3-mini—

    Not directly comparable

  • HealthBench Professional (raw)

    Claude Opus 573.4%
    Source
    o3-mini—

    Not directly comparable

  • BioMysteryBench (human-solvable)

    Claude Opus 590.1%
    Source
    o3-mini—

    Not directly comparable

  • BioMysteryBench (human-difficult)

    Claude Opus 549.4%
    Source
    o3-mini—

    Not directly comparable

  • SpatialBench Verified

    Claude Opus 572.5%
    Source
    o3-mini—

    Not directly comparable

  • SingleCellBench

    Claude Opus 560.6%
    Source
    o3-mini—

    Not directly comparable

  • ProteinGym Hard

    Claude Opus 547.7%
    Source
    o3-mini—

    Not directly comparable

  • Protein Design

    Claude Opus 542.5%
    Source
    o3-mini—

    Not directly comparable

  • Organic chemistry V2

    Claude Opus 561.6%
    Source
    o3-mini—

    Not directly comparable

  • Protocols (troubleshooting)

    Claude Opus 561.1%
    Source
    o3-mini—

    Not directly comparable

  • Protocols (understanding)

    Claude Opus 578.4%
    Source
    o3-mini—

    Not directly comparable

  • GPQA Diamond (Vals)

    Claude Opus 593.4%
    Source
    o3-mini—

    Not directly comparable

  • MMLU-Pro (Vals)

    Claude Opus 591.6%
    Source
    o3-mini—

    Not directly comparable

  • MMLU

    Claude Opus 5—
    o3-mini86.9%
    Source

    Not directly comparable

  • GPQA

    Claude Opus 5—
    o3-mini77.2%
    Source

    Not directly comparable

Math

  • IMO 2026

    Claude Opus 542/42
    Source
    o3-mini—

    Not directly comparable

  • RiemannBench (no tools)

    Claude Opus 560.0%
    Source
    o3-mini—

    Not directly comparable

  • RiemannBench (tools)

    Claude Opus 579.0%
    Source
    o3-mini—

    Not directly comparable

  • ArXivMath Jun. 2026 (no tools)

    Claude Opus 590.8%
    Source
    o3-mini—

    Not directly comparable

  • ArXivMath Jun. 2026 (tools)

    Claude Opus 591.3%
    Source
    o3-mini—

    Not directly comparable

  • AIME 2024

    Claude Opus 5—
    o3-mini87.3%
    Source

    Not directly comparable

Multilingual

  • GMMLU

    Claude Opus 592.5%
    Source
    o3-mini—

    Not directly comparable

  • MILU

    Claude Opus 592.1%
    Source
    o3-mini—

    Not directly comparable

  • INCLUDE

    Claude Opus 589.8%
    Source
    o3-mini—

    Not directly comparable

Multimodal

  • Chartography (no tools)

    Claude Opus 529.6%
    Source
    o3-mini—

    Not directly comparable

  • Chartography (tools)

    Claude Opus 583.0%
    Source
    o3-mini—

    Not directly comparable

  • BenchCAD Vision2Code (no tools)

    Claude Opus 50.366
    Source
    o3-mini—

    Not directly comparable

  • BenchCAD Vision2Code (tools)

    Claude Opus 50.821
    Source
    o3-mini—

    Not directly comparable

  • GDP.pdf (no tools)

    Claude Opus 583.4%
    Source
    o3-mini—

    Not directly comparable

  • GDP.pdf (tools)

    Claude Opus 585.5%
    Source
    o3-mini—

    Not directly comparable

  • OfficeQA

    Claude Opus 578.1%
    Source
    o3-mini—

    Not directly comparable

  • OfficeQA Pro

    Claude Opus 566.9%
    Source
    o3-mini—

    Not directly comparable

Instruction following

  • IFEval

    Claude Opus 5—
    o3-mini93.9%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Claude Opus 5 or o3-mini?

Claude Opus 5 has the higher public score, 80.66 versus 48.06, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.

Which is better for coding, Claude Opus 5 or o3-mini?

Claude Opus 5 leads the public coding lane, 75.6 to 40.6, with Supported evidence for both models and non-overlapping 90% intervals.

Which is better for agentic tasks, Claude Opus 5 or o3-mini?

O3-mini is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Claude Opus 5 or o3-mini?

For the stated presets, chat costs $0.0175 on Claude Opus 5 and $0.0033 on o3-mini; repository review costs $0.325 and $0.0682; the cache-heavy agent loop costs $0.45 and $0.286. o3-mini does not fit this workload in one request. o3-mini has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Claude Opus 5 or o3-mini?

Claude Opus 5 has the larger documented context window: 1M, compared with 200K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 4, 2026

Watch Claude Opus 5 vs o3-mini

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

Read a sample issue

Join 2,000+ readers.