Skip to main content
AI Choice Engine

Model comparison

Claude Opus 5.5 vs Gemini 3.8 Flash

Anthropic against Google, compared on context, price, and verified benchmark results.

Catalog record checked September 26, 2026Individual provider fields may changeEvidence confidence: High — see receipts below

Anthropic

Claude Opus 5.5

Frontier

vs

Google

Gemini 3.8 Flash

Balanced

AI model capability comparison
SpecificationClaude Opus 5.5Gemini 3.8 Flash
ProviderAnthropicGoogle
TierFrontierBalanced
Context window1MWinner: 1.05M
Max outputWinner: 128K66K
Input / 1M tokens$4Winner: $0.75
Output / 1M tokens$20Winner: $3.75
WeightsClosedClosed
ParametersNot disclosedUnverifiedNot disclosedUnverified
Reasoning levelsadaptivelow, medium, high
Modalitiestext, imagetext, image, video, audio, pdf
API model idclaude-opus-5-5gemini-3.8-flash
ReleasedSeptember 22, 2026September 2, 2026
Artificial Analysis Intelligence Index [max] (2026-09-26)57.6Not verifiedUnverified
Artificial Analysis Intelligence Index [high] (2026-09-26)Not verifiedUnverified40.9
Humanity's Last Exam [max] (2026-09-26)61.4Not verifiedUnverified
Humanity's Last Exam (2026-09-02)Not verifiedUnverified54.9
Terminal-Bench 4.0 [max] (2026-09-26)59.6Not verifiedUnverified
Terminal-Bench 4.0 [xhigh] (2026-09-22)66.4Not verifiedUnverified
Terminal-Bench 2.1 (2026-09-02)Not verifiedUnverified89.4

Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

  • 2026-09-26
    Artificial Analysis Terminal-Bench 4.0 (independent AA run, part of Intelligence Index v4.3.2)

    Agentic terminal work: long multi-step tasks executed in a sandboxed shell environment.

    Comparable with caveatNOT comparable with Terminal-Bench 2.x or 3.0 — 4.0 uses a new, non-overlapping task set. Within 4.0, scores from different harnesses (tbench.ai agent entries vs Artificial Analysis runs) are not interchangeable.

  • 2026-09-26
    Artificial Analysis Humanity's Last Exam (independent, 2,158 text-only questions)

    Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise.

    Comparable with caveatSubset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.

  • 2026-09-26
    Artificial Analysis

    Composite index blending reasoning, knowledge, and coding evals into one 0–100 score.

    Comparable with caveatOnly same-version scores are comparable. v4.3.2 was rebaselined (the top score fell from 66 on v4.1.1 to ~58), so v4.1.1 figures must not be compared with v4.3.2 figures — check measuredAt.

  • 2026-09-22
    Anthropic — Claude Opus 5.5 announcement (vendor; conflicts with AA's independent 59.6 — harness difference preserved)

    Agentic terminal work: long multi-step tasks executed in a sandboxed shell environment.

    Comparable with caveatNOT comparable with Terminal-Bench 2.x or 3.0 — 4.0 uses a new, non-overlapping task set. Within 4.0, scores from different harnesses (tbench.ai agent entries vs Artificial Analysis runs) are not interchangeable.

  • 2026-09-02
    Google official blog (vendor, HLE-Verified full set)

    Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise.

    Comparable with caveatSubset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.

  • 2026-09-02
    Google launch eval table (transcribed by Vellum)

    Agentic terminal work: multi-step tasks executed in a sandboxed shell environment.

    Comparable with caveatNot comparable with Terminal-Bench 3.0 or 4.0 (different task sets) or v1; harness configuration (container, time limits) also shifts results.

Pricing tiers

Claude Opus 5.5: $4/$20 per MTok, no long-context surcharge. Cache reads $0.20; 5-minute cache writes $5, 1-hour writes $8. Batch $2/$10; Fast mode $8/$40. Batches API allows 300K output with the output-300k-2026-03-24 beta header. Knowledge cutoff Jun 2026; retirement not before 2027-09-22.

Gemini 3.8 Flash: Intro $0.75/$3.75 per MTok through 2026-12-31, rising to $1.50/$7.50 from 2027-01-01; batch/Flex half price. Free tier available. Companion Gemini 3.8 Flash Cyber (defensive security) is restricted to the Fairwind Program with no public pricing.

FrontierRecord checked September 26, 2026

Claude Opus 5.5

Claude Opus 5.5 is Anthropic's default model for agentic coding and knowledge work — Anthropic says it performs near Fable 5.1 on most work at about 40% lower running cost than Opus 5, and it leads the Artificial Analysis Intelligence Index v4.3.2.

Best for

  • Complex agentic coding
  • Enterprise knowledge work
  • Default frontier model

Watch out

Breaking changes from Opus 5: adaptive thinking cannot be disabled (effort runs low to max, default medium) and forced tool use returns an error. Verbose at max effort, so cap output on cost-sensitive routes.

BalancedRecord checked September 26, 2026

Gemini 3.8 Flash

Gemini 3.8 Flash is Google's most capable workhorse Flash — within a point of the top of DeepSWE 1.1 at a fraction of frontier cost per task.

Best for

  • Agentic coding at scale
  • Mid-difficulty engineering
  • Multimodal pipelines

Watch out

Intro pricing doubles on 2027-01-01, and Google says it can consume more tokens than 3.7 Flash — 3.7 Flash stays available for efficiency-first workloads.

Benchmark

DeepSWE 1.1 in context

Only Gemini 3.8 Flash has a published DeepSWE 1.1 result. It is shown against the wider field, with cost per completed task alongside the score.

Local leader

GPT-6 Astra [xhigh]

74%

Rows shown

28

Best published Pass@1 per model (Datacurve's default view)

Snapshot date

2026-09-26

Mirrored from deepswe.datacurve.ai

DeepSWE 1.1 pass@10%16%32%48%64%80%$0$4.50$9.00$13.50$18.00$22.50$27.00Avg cost per taskGPT-6 Astra [xhigh]: 74% · $4.43 · 30k tokens · 29 stepsGemini 3.8 Flash [high]: 74% · $2.36 · 143k tokens · 166 stepsClaude Opus 5 [max]: 74% · $11.84 · 118k tokens · 99 stepsGPT-5.6 Sol [max]: 73% · $8.39 · 60k tokens · 61 stepsClaude Fable 5 [xhigh]: 70% · $13.41 · 80k tokens · 68 stepsGPT-5.6 Terra [max]: 70% · $4.95 · 72k tokens · 76 stepsGLM 5.3 [max]: 69% · $3.99 · 80k tokens · 124 stepsKimi K3 [max]: 69% · $4.65 · 82k tokens · 98 stepsGrok 4.6 [medium]: 68% · $3.45 · 50k tokens · 70 stepsGPT-5.6 Luna [max]: 67% · $3.03 · 73k tokens · 102 stepsGPT-5.5 [xhigh]: 67% · $7.23 · 46k tokens · 82 stepsGemini 3.7 Flash [medium]: 66% · $2.03 · 94k tokens · 117 stepsGLM 5.3 Flash [max]: 63% · $0.48 · 73k tokens · 123 stepsDeepSeek V4-Pro [max]: 63% · $0.24 · 106k tokens · 155 stepsClaude Opus 4.8 [max]: 59% · $13.22 · 135k tokens · 120 stepsQwen3.8-Max [xhigh]: 58% · $3.73 · 95k tokens · 111 stepsMuse Spark 1.2 [xhigh]: 55% · $3.70 · 99k tokens · 101 stepsClaude Sonnet 5 [max]: 54% · $26.40 · 214k tokens · 268 stepsGrok 4.5 [high]: 54% · $2.42 · 36k tokens · 61 stepsDeepSeek V4-Flash [max]: 53% · $0.10 · 108k tokens · 153 stepsMuse Spark 1.1 [xhigh]: 53% · $2.36 · 74k tokens · 96 stepsGPT-5.4 [xhigh]: 52% · $5.65 · 71k tokens · 70 stepsGemini 3.6 Flash [high]: 47% · $4.42 · 96k tokens · 117 stepsGLM 5.2 [max]: 44% · $3.92 · 78k tokens · 129 stepsGemini 3.5 Flash [high]: 36% · $3.45 · 76k tokens · 105 stepsKimi K2.7 Code: 31% · $2.82 · 59k tokens · 149 stepsClaude Sonnet 4.6 [high]: 30% · $5.52 · 76k tokens · 134 stepsGemini 3.1 Pro [high]: 12% · $2.14 · 28k tokens · 76 steps

Better is toward the top-right (higher pass rate, lower cost). X-axis is reversed to match DeepSWE’s public chart. v1.1 uses average cost / tokens / steps; v1 uses published medians.

DeepSWE 1.1 leaderboard with pass rate, cost, tokens, and steps per task
#ModelPass@1Cost / taskTokens / taskSteps / task
1GPT-6 Astra [xhigh]74%$4.4330k29
2Gemini 3.8 Flash [high]74%$2.36143k166
3Claude Opus 5 [max]74%$11.84118k99
4GPT-5.6 Sol [max]73%$8.3960k61
5Claude Fable 5 [xhigh]70%$13.4180k68
6GPT-5.6 Terra [max]70%$4.9572k76
7GLM 5.3 [max]69%$3.9980k124
8Kimi K3 [max]69%$4.6582k98
9Grok 4.6 [medium]68%$3.4550k70
10GPT-5.6 Luna [max]67%$3.0373k102
11GPT-5.5 [xhigh]67%$7.2346k82
12Gemini 3.7 Flash [medium]66%$2.0394k117
13GLM 5.3 Flash [max]63%$0.4873k123
14DeepSeek V4-Pro [max]63%$0.24106k155
15Claude Opus 4.8 [max]59%$13.22135k120
16Qwen3.8-Max [xhigh]58%$3.7395k111
17Muse Spark 1.2 [xhigh]55%$3.7099k101
18Claude Sonnet 5 [max]54%$26.40214k268
19Grok 4.5 [high]54%$2.4236k61
20DeepSeek V4-Flash [max]53%$0.10108k153
21Muse Spark 1.1 [xhigh]53%$2.3674k96
22GPT-5.4 [xhigh]52%$5.6571k70
23Gemini 3.6 Flash [high]47%$4.4296k117
24GLM 5.2 [max]44%$3.9278k129
25Gemini 3.5 Flash [high]36%$3.4576k105
26Kimi K2.7 Code31%$2.8259k149
27Claude Sonnet 4.6 [high]30%$5.5276k134
28Gemini 3.1 Pro [high]12%$2.1428k76

“Best per model” shows each model’s highest published Pass@1, as Datacurve’s own board does; switch to all effort levels to see every configuration. Small gaps may not be statistically meaningful — confirm on deepswe.datacurve.ai.

When the cheaper one wins

Gemini 3.8 Flash is cheaper on output at $3.75 per million tokens against $20 for Claude Opus 5.5 — about 5.3×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.

Run the model picker

Evidence confidence: High

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

  • Pricing verified on both sides — Input and output rates are verified for both models.
  • 4/5 core specs verified on both sides — Not published for at least one side: parameter count.
  • 2 shared named benchmarks with differing scores — Measured on: Artificial Analysis Intelligence Index, Humanity's Last Exam.
  • Verified within the last 90 days — Newest catalog check was 2 days ago.
  • Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Common questions

Claude Opus 5.5 vs Gemini 3.8 Flash

Answered from the verified figures on this page rather than general guidance.

Is Claude Opus 5.5 or Gemini 3.8 Flash cheaper for input?
Gemini 3.8 Flash is cheaper at $0.75 per million input tokens, against $4 for Claude Opus 5.5 — roughly 5.3× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Claude Opus 5.5 has tiered pricing: $4/$20 per MTok, no long-context surcharge. Cache reads $0.20; 5-minute cache writes $5, 1-hour writes $8. Batch $2/$10; Fast mode $8/$40. Batches API allows 300K output with the output-300k-2026-03-24 beta header. Knowledge cutoff Jun 2026; retirement not before 2027-09-22. Gemini 3.8 Flash has tiered pricing: Intro $0.75/$3.75 per MTok through 2026-12-31, rising to $1.50/$7.50 from 2027-01-01; batch/Flex half price. Free tier available. Companion Gemini 3.8 Flash Cyber (defensive security) is restricted to the Fairwind Program with no public pricing.
Is Claude Opus 5.5 or Gemini 3.8 Flash cheaper for output?
Gemini 3.8 Flash is cheaper at $3.75 per million output tokens, against $20 for Claude Opus 5.5 — roughly 5.3× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Claude Opus 5.5 has tiered pricing: $4/$20 per MTok, no long-context surcharge. Cache reads $0.20; 5-minute cache writes $5, 1-hour writes $8. Batch $2/$10; Fast mode $8/$40. Batches API allows 300K output with the output-300k-2026-03-24 beta header. Knowledge cutoff Jun 2026; retirement not before 2027-09-22. Gemini 3.8 Flash has tiered pricing: Intro $0.75/$3.75 per MTok through 2026-12-31, rising to $1.50/$7.50 from 2027-01-01; batch/Flex half price. Free tier available. Companion Gemini 3.8 Flash Cyber (defensive security) is restricted to the Fairwind Program with no public pricing.
Which has the larger context window, Claude Opus 5.5 or Gemini 3.8 Flash?
Gemini 3.8 Flash accepts 1.05M tokens against 1M for Claude Opus 5.5. This only matters if you routinely send very long documents or large codebases.
Do Claude Opus 5.5 and Gemini 3.8 Flash support the same reasoning levels?
Claude Opus 5.5 exposes adaptive, while Gemini 3.8 Flash exposes low, medium, high.
Should I use Claude Opus 5.5 or Gemini 3.8 Flash?
Claude Opus 5.5 is the frontier tier and Gemini 3.8 Flash the balanced tier. The useful question is whether your hardest task actually fails on the cheaper one — most production volume such as classification, extraction and summarisation does not.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

  • Input price: Gemini 3.8 Flash costs $0.75 per 1M tokens versus $4 for Claude Opus 5.5 — a 5.3x difference at the headline tier.
  • Context: Gemini 3.8 Flash takes 1.05M against 1M for Claude Opus 5.5 — only decisive if your prompts approach the smaller window.
  • Measured capability: Claude Opus 5.5 leads Artificial Analysis Intelligence Index 57.6 to 40.9 (measured 2026-09-26).
  • Positioning: Claude Opus 5.5 sits in the frontier tier, Gemini 3.8 Flash in the balanced tier — most production volume (classification, extraction, summarisation) does not need the pricier tier.

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.