Updated October 17, 2026. Rank says Claude Opus 4.8 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Claude Opus 4.8 has the higher public score estimate, 70.01 versus 69.25, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 17 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
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.
Tool use, computer use, and multi-step task completion
Gemini 3.8 Flash
Gemini 3.8 Flash has the higher public agentic point estimate, 65.9 to 63.4, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
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.
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. Claude Opus 4.8 has no published cached-input rate, so cached tokens use its listed input rate.
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.
Code generation, repair, and software-engineering tasks
No clear pick
The like-for-like coding result is a practical tie on the public lane (within 0.5 points).
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
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.
Like-for-like · BenchAlign v5.8
Gemini 3.8 Flash has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
OSWorld 2.0Agentic
Normalized gap 38.4FrontierMath v2 (Tier 4)Math
Normalized gap 34.1ARC-AGI-2Reasoning
Normalized gap 17.1FrontierMath v2 (Tiers 1-3)Math
Normalized gap 11.6ARC-AGI-3Reasoning
Normalized gap 8.8Each row shows the public-lane category score for both models: the BenchAlign v5.8 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.
| Category | Claude Opus 4.8 | Gemini 3.8 Flash | Basis | Reading |
|---|---|---|---|---|
| Agentic | 63.4Supported · #19/128 | 65.9Supported · #16/128 | Like-for-likeBenchAlign v5.8 lane · 13 vs 9 public rows | Gemini 3.8 Flash leads · intervals overlap |
| Coding | 60.7Supported · #19/150 | 61.0Supported · #17/150 | Like-for-likeBenchAlign v5.8 lane · 11 vs 8 public rows | Practical tie |
| Reasoning | 62.8#24/28 | 74.3#17/28 | Like-for-likeProvisional lane · 2 vs 2 weighted rows | Gemini 3.8 Flash leads |
| Knowledge | 72.0Supported · #15/184 | 73.5Supported · #13/184 | Like-for-likeBenchAlign v5.8 lane · 6 vs 6 public rows | Gemini 3.8 Flash leads · intervals overlap |
| Multimodal | 91.2#5/54 | 87.3#9/54 | Directional onlyProvisional lane · 2 vs 0 weighted rows | Directional only |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | 75.4#65/148 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 84.4#1/12 | 69.7Unranked · 2 rankable rows | Not comparableProvisional lane · 3 vs 2 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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.
1K fresh input + 500 output tokens
Gemini 3.8 Flash has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Gemini 3.8 Flash has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Gemini 3.8 Flash has the lower modeled cost
Claude Opus 4.8 has no published cached-input rate, so cached tokens use its listed input rate.
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
Claude Opus 4.8
Gemini 3.8 Flash
Claude Opus 4.8
claude-opus-4-8
Anthropic model overviewGemini 3.8 Flash
gemini-3.8-flash
Google Gemini 3.8 Flash API documentationA missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Opus 4.8
Not published
Gemini 3.8 Flash
$0.075 per 1M cached input tokens
Google Gemini API pricingClaude Opus 4.8
text, image
Anthropic model overviewGemini 3.8 Flash
text, image, video, audio, pdf
Google Gemini 3.8 Flash API documentationClaude Opus 4.8
Gemini 3.8 Flash
Claude Opus 4.8
Generally Available · Claude API
Anthropic model overviewGemini 3.8 Flash
Generally Available · Gemini API, Google AI Studio, Android Studio, Stitch, Gemini app, Gemini Enterprise, Google AI Mode, Google Sheets, Google Antigravity
Google Gemini 3.8 Flash and Gemini 3.8 Flash Cyber launchClaude Opus 4.8
Reasoning
Gemini 3.8 Flash
Reasoning
Claude Opus 4.8
Proprietary
Gemini 3.8 Flash
Proprietary
Claude Opus 4.8
Proprietary
Gemini 3.8 Flash
Proprietary
Claude Opus 4.8
2026-05-28
Gemini 3.8 Flash
2026-09-02
Claude Opus 4.8 has the higher public score estimate, 70.01 versus 69.25, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
The like-for-like coding row is a practical tie on the public lane, 60.7 against 61, inside the 0.5-point band BenchLM treats as level.
Gemini 3.8 Flash has the higher public agentic tasks point estimate, 65.9 to 63.4, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
For the stated presets, chat costs $0.0175 on Claude Opus 4.8 and $0.00263 on Gemini 3.8 Flash; repository review costs $0.325 and $0.04875; the cache-heavy agent loop costs $1.35 and $0.0675. Claude Opus 4.8 has no published cached-input rate, so cached tokens use its listed input rate.
Both models list the same context window, 1M.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 3.0
Not directly comparable
Terminal-Bench 2.1
Gemini 3.8 Flash leads this result
BrowseComp
Not directly comparable
DeepSearchQA
Not directly comparable
OSWorld-Verified
Not directly comparable
Finance Agent v2
Gemini 3.8 Flash leads this result
MCP Atlas
Not directly comparable
Toolathlon
Not directly comparable
Gert Labs
Not directly comparable
ResearchClawBench
Not directly comparable
OSWorld 2.0
Gemini 3.8 Flash leads this result
Terminal-Bench 2.1 (Vals)
Gemini 3.8 Flash leads this result
MazeBench
Gemini 3.8 Flash leads this result
Terminal-Bench 4.0
Not directly comparable
ApprenticeBench
Not directly comparable
Hermes Index
Not directly comparable
Hermes Bench
Not directly comparable
SWE-bench Verified
Not directly comparable
SWE-bench Pro
Not directly comparable
SWE Multilingual
Not directly comparable
SWE Multimodal
Not directly comparable
Terminal-Bench 2.1
Gemini 3.8 Flash leads this result
cursorBench31
Not directly comparable
CursorBench 3.2
Shared sourceGemini 3.8 Flash leads this result
FrontierCode 1.1 Main
Not directly comparable
LiveCodeBench (Vals)
Gemini 3.8 Flash leads this result
SWE-bench (Vals)
Claude Opus 4.8 leads this result
PostTrainBench v1.1
Not directly comparable
DeepSWE
Not directly comparable
FrontierSWE v2
Not directly comparable
CursorBench 4.0
Not directly comparable
Bug Hunt Bench
Not directly comparable
OfficeQA Pro
Not directly comparable
ScreenSpot Pro
Not directly comparable
CharXiv
Not directly comparable
CharXiv w/o tools
Gemini 3.8 Flash leads this result
LVBench
Not directly comparable
GPQA
Not directly comparable
GPQA-D
Not directly comparable
HLE
Not directly comparable
HLE w/o tools
Not directly comparable
GPQA Diamond (Vals)
Gemini 3.8 Flash leads this result
MMLU-Pro (Vals)
Gemini 3.8 Flash leads this result
HLE-Verified
Not directly comparable
LABBench2
Not directly comparable
BioMysteryBench (human-solvable)
Not directly comparable
BioMysteryBench (human-difficult)
Not directly comparable
INCLUDE
Not directly comparable
Gray Swan IPI (15 attempts)
Not directly comparable
USAMO 2026
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Shared sourceClaude Opus 4.8 leads this result
FrontierMath v2 (Tier 4)
Shared sourceClaude Opus 4.8 leads this result
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,600+ readers.
Last updated October 17, 2026
