Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

Claude Opus 5.5 vs Gemini 3.8 Flash

Decision reading

Claude Opus 5.5 has the higher public score estimate, 81.03 versus 74.15, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

7 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Anthropic logo
Model A
Claude Opus 5.5

Anthropic

81.03/100

Estimated · Public rank #5

90% interval 56.4–92.5

Google logo
Model B
Gemini 3.8 Flash

Google

74.15/100

Supported · Public rank #10

90% interval 69.3–79.1

Updated September 22, 2026. Rank says Claude Opus 5.5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

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.

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Claude Opus 5.5

    Claude Opus 5.5 leads on the public agentic lane, 82.7 to 66.6, with Supported evidence for both models, although the 90% intervals overlap.

    Confidence: limited

  • Chat turn cost

    1K fresh input + 500 output tokens

    Gemini 3.8 Flash

    Gemini 3.8 Flash 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

    Gemini 3.8 Flash

    Gemini 3.8 Flash 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

    Gemini 3.8 Flash

    Gemini 3.8 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Claude Opus 5.5 is scored on Estimated evidence for coding, so the reading is 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

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

76.0Claude Opus 5.567.1Gemini 3.8 Flash

Directional only · BenchAlign

Claude Opus 5.5 scores higher, but at least one score rests on Estimated evidence or a different benchmark set. Directional only, no winner.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboardShortlist models for this job

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
7
Claude Opus 5.5 only
41
Gemini 3.8 Flash only
14
Like-for-like categories
1 / 8

4 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

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.

Agentic

Like-for-like
Claude Opus 5.5
82.7
Supported · #1/156
Gemini 3.8 Flash
66.6
Supported · #12/156
Basis
BenchAlign lane · 11 vs 6 public rows
Reading
Claude Opus 5.5 leads · intervals overlap

Coding

Directional only
Claude Opus 5.5
76.0
Estimated · #4/159
Gemini 3.8 Flash
67.1
Supported · #9/159
Basis
BenchAlign lane · 9 vs 7 public rows
Reading
Directional only

Reasoning

Directional only
Claude Opus 5.5
78.5
#4/19
Gemini 3.8 Flash
76.9
#8/19
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Directional only

Multimodal

Directional only
Claude Opus 5.5
88.8
#3/50
Gemini 3.8 Flash
82.9
#9/50
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Directional only

Knowledge

Directional only
Claude Opus 5.5
81.5
Estimated · #3/187
Gemini 3.8 Flash
74.2
Supported · #7/187
Basis
BenchAlign lane · 17 vs 6 public rows
Reading
Directional only

Multilingual

Not comparable
Claude Opus 5.5
Not ranked
Gemini 3.8 Flash
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Claude Opus 5.5
Not ranked
Gemini 3.8 Flash
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Claude Opus 5.5
Not ranked
Gemini 3.8 Flash
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 5.5
$0.014
Fits in one request
Gemini 3.8 Flash
$0.00262
Fits in one request

Gemini 3.8 Flash has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Opus 5.5
$0.26
Fits in one request
Gemini 3.8 Flash
$0.04875
Fits in one request

Gemini 3.8 Flash 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 5.5
$0.32
Fits in one request
Gemini 3.8 Flash
$0.0675
Fits in one request

Gemini 3.8 Flash 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.

Reasoning profile

Claude Opus 5.5

Reasoning

Gemini 3.8 Flash

Reasoning

Weight access

Claude Opus 5.5

Proprietary

Gemini 3.8 Flash

Proprietary

License

Claude Opus 5.5

Proprietary

Gemini 3.8 Flash

Proprietary

Release date

Claude Opus 5.5

2026-09-22

Gemini 3.8 Flash

2026-09-02

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 5.5 has the higher public score estimate, 81.03 versus 74.15, but the 90% score intervals overlap.
Workload cost
Repository review: $0.26 vs $0.04875. Cache-heavy agent loop: $0.32 vs $0.0675.
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 evidence62 rows

Agentic

  • Terminal-Bench 4.0

    Claude Opus 5.566.40%
    Source
    Gemini 3.8 Flash19.10%
    Source

    Claude Opus 5.5 leads this result

  • Terminal-Bench-Science 0.1

    Claude Opus 5.558.7%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • AutomationBench

    Claude Opus 5.540.0%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • HLE w/ tools

    Claude Opus 5.567.7%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • OSWorld 2.0

    Claude Opus 5.548.7%
    Source
    Gemini 3.8 Flash59.0%
    Source

    Gemini 3.8 Flash leads this result

  • LAB all-pass (Harvey held-out)

    Claude Opus 5.58.3%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • LAB criterion-pass (Harvey held-out)

    Claude Opus 5.591.2%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Toolathlon-Verified

    Claude Opus 5.577.8%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Toolathlon Verified Pass@3

    Claude Opus 5.582.4%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Toolathlon Verified Pass³

    Claude Opus 5.572.2%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Toolathlon Verified avg. turns

    Claude Opus 5.526.9 turns
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Finance Agent v2

    Claude Opus 5.5—
    Gemini 3.8 Flash61.4%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Opus 5.5—
    Gemini 3.8 Flash89.4%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Claude Opus 5.5—
    Gemini 3.8 Flash81.3%
    Source

    Not directly comparable

  • ApprenticeBench

    Claude Opus 5.5—
    Gemini 3.8 Flash24%
    Source

    Not directly comparable

Coding

  • FrontierCode 1.1 Main

    Claude Opus 5.554.4%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • cursorBench40

    Shared source
    Claude Opus 5.557.8%
    Gemini 3.8 Flash39.6%

    Claude Opus 5.5 leads this result

  • SWE-bench Pro

    Claude Opus 5.589.9%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • SWE Multilingual

    Claude Opus 5.593.9%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • SWE Multimodal

    Claude Opus 5.561.4%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • DeepSWE

    Claude Opus 5.574.2%
    Source
    Gemini 3.8 Flash73.8%
    Source

    Claude Opus 5.5 leads this result

  • FrontierCode 1.1 Extended

    Claude Opus 5.563.6%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • FrontierSWE v2

    Claude Opus 5.562.3%
    Source
    Gemini 3.8 Flash19.6%
    Source

    Claude Opus 5.5 leads this result

  • ProgramBench

    Claude Opus 5.591.2%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Opus 5.5—
    Gemini 3.8 Flash89.4%
    Source

    Not directly comparable

  • cursorBench32

    Claude Opus 5.5—
    Gemini 3.8 Flash69.2%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    Claude Opus 5.5—
    Gemini 3.8 Flash89.5%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    Claude Opus 5.5—
    Gemini 3.8 Flash80.0%
    Source

    Not directly comparable

Multimodal

  • Chartography (tools)

    Claude Opus 5.589.0%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Chartography (no tools)

    Claude Opus 5.564.4%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • BenchCAD Vision2Code (no tools)

    Claude Opus 5.50.730
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • BenchCAD Vision2Code (tools)

    Claude Opus 5.50.962
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Biomedical image analysis

    Claude Opus 5.571.4%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • OfficeQA

    Claude Opus 5.578.9%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • OfficeQA Pro

    Claude Opus 5.567.7%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • CharXiv w/o tools

    Claude Opus 5.5—
    Gemini 3.8 Flash86.2%
    Source

    Not directly comparable

  • LVBench

    Claude Opus 5.5—
    Gemini 3.8 Flash87.1%
    Source

    Not directly comparable

Knowledge

  • HLE

    Claude Opus 5.567.7%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • HLE w/o tools

    Claude Opus 5.564.4%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • HealthBench (raw)

    Claude Opus 5.568.1%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • HealthBench (length-adjusted)

    Claude Opus 5.560.6%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • HealthBench Professional

    Claude Opus 5.565.6%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • HealthBench Professional (raw)

    Claude Opus 5.577.1%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • BioMysteryBench (human-solvable)

    Claude Opus 5.589.3%
    Source
    Gemini 3.8 Flash88.8%
    Source

    Claude Opus 5.5 leads this result

  • BioMysteryBench (human-difficult)

    Claude Opus 5.550.0%
    Source
    Gemini 3.8 Flash56.5%
    Source

    Gemini 3.8 Flash leads this result

  • SpatialBench Verified

    Claude Opus 5.572.0%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • SingleCellBench

    Claude Opus 5.561.2%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Morphology-to-molecule matching

    Claude Opus 5.534.0%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Medicinal chemistry

    Claude Opus 5.563.5%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Protein Design

    Claude Opus 5.560.2%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Protein Design library ranking

    Claude Opus 5.556.0%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • De novo protein-binder design

    Claude Opus 5.582.6%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Protocols (troubleshooting)

    Claude Opus 5.573.7%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • Protocols (understanding)

    Claude Opus 5.569.0%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • HLE-Verified

    Claude Opus 5.5—
    Gemini 3.8 Flash54.9%
    Source

    Not directly comparable

  • LABBench2

    Claude Opus 5.5—
    Gemini 3.8 Flash86.2%
    Source

    Not directly comparable

  • GPQA Diamond (Vals)

    Claude Opus 5.5—
    Gemini 3.8 Flash94.4%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    Claude Opus 5.5—
    Gemini 3.8 Flash90.2%
    Source

    Not directly comparable

Multilingual

  • GMMLU

    Claude Opus 5.594.3%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • MILU

    Claude Opus 5.593.1%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

Math

  • ArXivMath Aug. 2026 (no tools)

    Claude Opus 5.591.2%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

  • ArXivMath Aug. 2026 (tools)

    Claude Opus 5.596.9%
    Source
    Gemini 3.8 Flash—

    Not directly comparable

Questions

Which is better, Claude Opus 5.5 or Gemini 3.8 Flash?

Claude Opus 5.5 has the higher public score estimate, 81.03 versus 74.15, 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 Opus 5.5 or Gemini 3.8 Flash?

Claude Opus 5.5 scores higher for coding on the public lane, 76 to 67.1. Claude Opus 5.5 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Claude Opus 5.5 or Gemini 3.8 Flash?

Claude Opus 5.5 leads the public agentic tasks lane, 82.7 to 66.6, with Supported evidence for both models, although the 90% intervals overlap.

Which costs less, Claude Opus 5.5 or Gemini 3.8 Flash?

For the stated presets, chat costs $0.014 on Claude Opus 5.5 and $0.00263 on Gemini 3.8 Flash; repository review costs $0.26 and $0.04875; the cache-heavy agent loop costs $0.32 and $0.0675. Costs use the listed standard API rates.

Which has the larger context window, Claude Opus 5.5 or Gemini 3.8 Flash?

Both models list the same context window, 1M.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 22, 2026

Watch Claude Opus 5.5 vs Gemini 3.8 Flash

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

Read a sample issue

Join 2,000+ readers.