Across 24 comparable benchmarks, Gemini 3.8 Flash has better reported results on 23 and worse on 1. 3 further shared results are listed below, each with the reason it is not counted.
Moderate evidence24 of 27 shared results countedHow we compare
Price basis: Current effective rates. The price section below shows the applicable periods.
| Fact | Gemini 3.8 Flash | Haiku 4.5 |
|---|---|---|
| Context window | 1M tokens | 200K tokens |
| Input / 1M | $0.750 | $1.00 |
| Output / 1M | $3.75 | $5.00 |
| Blended (4:1) | $0.432 | $1.15 |
| Status | Available | Available |
| Released | September 2, 2026 | October 15, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates β set your own mix.
Mean of 15 shared benchmarks grouped by capability on a 0β100 scale. How averages are built
Gemini 3.8 Flash ahead on 3 of 3 counted
Gemini 3.8 Flash ahead on 1 of 1 counted
Gemini 3.8 Flash ahead on 3 of 4 counted
Gemini 3.8 Flash ahead on 2 of 2 counted
Gemini 3.8 Flash ahead on 9 of 9 counted
No shared comparable results for Mathematics, Computer & tool use, Research & search, Long context, Cybersecurity.
Published scores, with matching modes where available. Gaps show Gemini 3.8 Flash relative to Haiku 4.5. Reading the results
| Benchmark | Gemini 3.8 Flash | Haiku 4.5 | Gap |
|---|---|---|---|
| Code MigrationMaintenance & Optimization Β· Hidden-test pass rate (%) | 36.5Thinking High Β· tools | 7.5β Thinking Β· tools | +29.0 pts#37 vs #67 of 79 |
| SWE-Bench Pro V2 HardRepository Engineering Β· Resolve Rate (%, pass@1) | 58.8Thinking High Β· tools | 25.5β Extra-High Β· tools | +33.3 pts#18 vs #21 of 21 |
| Vibe Code Bench v1.1Code Generation & Editing Β· Pass rate (%) | 78.7Thinking High Β· tools | 11.4β Thinking Β· tools | +67.3 pts#35 vs #102 of 121 |
| ARC-AGI-1Abstract Generalization Β· Score (%) | 98.5Thinking High Β· no tools | 47.7β Extended Β· no tools | +50.8 pts#1 vs #67 of 87 |
| ARC-AGI-2Abstract Generalization Β· Score (% solved); cost per task (USD)Not counted Β· Speed and cost telemetry is reported, not scored | 89.2Thinking High Β· no tools | 4.5β Extended Β· no tools | 19.8Γ#12 vs #70 of 80 |
| Vending-Bench 2Logical Planning Β· Money Balance (USD)Not counted Β· Speed and cost telemetry is reported, not scored | 5094Unspecified Reasoning Β· tools | 459Unspecified Reasoning Β· tools | 11.1Γ#38 vs #58 of 64 |
| GPQA DiamondScientific Reasoning Β· Accuracy | 95.3Thinking High Β· no tools | 73.3β Extended Β· no tools | +22.0 pts#7 vs #126 of 200 |
| SciCodeScientific Computing Β· Score | 56.6Thinking High Β· no tools | 42.2β Thinking Β· no tools | 1.34Γ#24 vs #72 of 98 |
| MedCodeClinical Workflows Β· Accuracy (%) | 48.1Thinking High Β· tools | 32.7β Thinking Β· tools | +15.5 pts#30 vs #81 of 97 |
| MedScribeClinical Workflows Β· Rubric pass rate (%) | 84.5Thinking High Β· tools | 85.2β Thinking Β· tools | β0.7 pts#34 vs #30 of 99 |
| GDP.pdfDocuments & Charts Β· Task pass rate (%) | 22.8Thinking Medium Β· no tools | 3.8β Thinking Β· no tools | +19.0 pts#22 vs #78 of 96 |
| MMMU-ProVisual Understanding Β· Accuracy | 85.6Thinking High Β· no tools | 58.6β Thinking Β· no tools | +27.0 pts#7 vs #109 of 136 |
| AA-AnalystAgentData Analysis Β· pass^5 (%) | 46.3Thinking High Β· tools + web | 15.0β Thinking Β· tools + web | +31.3 pts#17 vs #32 of 39 |
| AutomationBenchOffice & Business Β· Pass Rate | 29.7Thinking Medium Β· toolsΒ· zapier-private-heldout | 0.46β Reported bestΒ· zapier-private-heldout | +29.2 pts#35 vs #62 of 64 |
| EMB (Excel Modeling)Finance Β· Accuracy (%) | 72.2Thinking High Β· tools | 22.7β Thinking Β· tools | +49.5 pts#10 vs #72 of 78 |
| Finance Agent v2Finance Β· Score | 61.4Thinking Β· tools | 31.0Thinking Β· tools | 1.98Γ#2 vs #68 of 75 |
| Harvey's Legal Agent BenchmarkLegal Β· Accuracy (%) | 10.0Thinking High Β· tools | 0.83β Thinking Β· tools | +9.2 pts#13 vs #41 of 52 |
| Legal Research BenchLegal Β· Score | 38.9Thinking High Β· tools | 10.6β Thinking Β· tools | 3.68Γ#39 vs #81 of 91 |
| Public Benefits Bench v1.1Service Workflows Β· Criterion pass rate (%) | 65.3Thinking High Β· tools | 54.3β Unspecified Reasoning Β· tools | +11.0 pts#22 vs #42 of 50 |
| SAGEService Workflows Β· Accuracy (%) | 35.1Thinking High Β· tools | 31.8β Thinking Β· tools | +3.2 pts#66 vs #71 of 82 |
| ΟΒ³-BankingService Workflows Β· Score | 45.8Thinking Medium Β· tools | 9.3β Thinking Β· tools | 4.92Γ#13 vs #95 of 120 |
| HLEKnowledge Exams Β· Accuracy | 44.5Reported best | 9.7β Extended Β· no tools | +34.8 pts#66 vs #129 of 151 |
| AA Intelligence Index v5.0.1Capability Indices Β· Index (0-100) | 30.8Thinking High Β· tools | 7.4β Thinking Β· tools | 4.15Γ#29 vs #54 of 62 |
| ECICapability Indices Β· ECI score (capability index, higher is better) | 157Reported best | 142Reported best | 1.10Γ#15 vs #90 of 168 |
| LiveBenchCross-capability Suites Β· Accuracy | 75.8Thinking High Β· no tools | 61.3β Thinking Β· no tools Β· 64K | +14.5 pts#30 vs #82 of 106 |
| LiveBench 2.0Cross-capability Suites Β· Overall score (equal-weight mean of 7 suite scores, 0-100) | 67.3Thinking High Β· tools | 46.0β Max Β· task tools | 1.46Γ#29 vs #48 of 51 |
| Vals IndexCapability IndicesNot counted Β· This metric has no better direction | 62.3Thinking High Β· tools | 22.9β Thinking Β· tools | β |
Maintenance & Optimization Β· Hidden-test pass rate (%)
Repository Engineering Β· Resolve Rate (%, pass@1)
Code Generation & Editing Β· Pass rate (%)
Abstract Generalization Β· Score (%)
Abstract Generalization Β· Score (% solved); cost per task (USD)
Not counted Β· Speed and cost telemetry is reported, not scored
Logical Planning Β· Money Balance (USD)
Not counted Β· Speed and cost telemetry is reported, not scored
Scientific Reasoning Β· Accuracy
Scientific Computing Β· Score
Clinical Workflows Β· Accuracy (%)
Clinical Workflows Β· Rubric pass rate (%)
Data Analysis Β· pass^5 (%)
Office & Business Β· Pass Rate
Finance Β· Accuracy (%)
Finance Β· Score
Legal Β· Accuracy (%)
Legal Β· Score
Service Workflows Β· Criterion pass rate (%)
Service Workflows Β· Accuracy (%)
Service Workflows Β· Score
Knowledge Exams Β· Accuracy
Capability Indices Β· Index (0-100)
Capability Indices Β· ECI score (capability index, higher is better)
Cross-capability Suites Β· Accuracy
Cross-capability Suites Β· Overall score (equal-weight mean of 7 suite scores, 0-100)
Capability Indices
Not counted Β· This metric has no better direction
A dash means no result is available.
Both models publish peak and off-peak prices. Each period is compared separately using the same token mix; hours follow each providerβs schedule.
Drag the handle above the bar for cache hits, the one below it for the input : output mix Β· 5% steps
Blended price = effective input rate at 90% cache hits Γ 80% + output rate Γ 20%
Gemini 3.8 Flash costs25%lessthan Haiku 4.5 per million tokens.Using current effective rates at this token mix.
Gemini 3.8 Flash: Listed text rates; pricing tier not confirmed.
Haiku 4.5: Standard pricing. Anthropic official pricing (platform.claude.com/docs/en/about-claude/pricing) verified 2026-11-13
| Price / 1M tokens | Gemini 3.8 Flash | Haiku 4.5 | Ratio |
|---|---|---|---|
| Input | $0.75 | $1.00 | 0.75Γ |
| Output | $3.75 | $5.00 | 0.75Γ |
| Cached input | $0.075 | $0.10 | 0.75Γ |
| Cache write | β | β | β |
| Blended | $0.864 | $1.15 | 0.75Γ |
Gemini 3.8 Flash costs50%morethan Haiku 4.5 per million tokens.Using standard list rates after promotions end at this token mix.
Gemini 3.8 Flash: Standard pricing. Google Gemini API official pricing (ai.google.dev/gemini-api/docs/pricing) verified 2026-10-21; paid tier; standard tier; scheduled price starting 2027-01-01
Haiku 4.5: Standard pricing. Anthropic official pricing (platform.claude.com/docs/en/about-claude/pricing) verified 2026-11-13
| Price / 1M tokens | Gemini 3.8 Flash | Haiku 4.5 | Ratio |
|---|---|---|---|
| Input | $1.50 | $1.00 | 1.50Γ |
| Output | $7.50 | $5.00 | 1.50Γ |
| Cached input | $0.15 | $0.10 | 1.50Γ |
| Cache write | β | β | β |
| Blended | $1.73 | $1.15 | 1.50Γ |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
Gemini 3.8 Flash relative to Haiku 4.5
No matching recorded settings for a cost summary.
Summary: 0 of 4 shared benchmarks have matching recorded settings and sources. The average is a geometric mean of 0 positive-cost ratios, one equal weight per benchmark. This benchmark set can include related tests and indexes; it is not a workload cost estimate.
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ or are not recorded; interpret the comparison with care.
Gemini 3.8 Flash
Haiku 4.5
Settings or sources differ or are not recorded; interpret the comparison with care.
Gemini 3.8 Flash
Haiku 4.5
Settings or sources differ or are not recorded; interpret the comparison with care.
Gemini 3.8 Flash
Haiku 4.5
Settings or sources differ or are not recorded; interpret the comparison with care.
Gemini 3.8 Flash
Haiku 4.5
| Benchmark | Gemini 3.8 Flash | Haiku 4.5 |
|---|---|---|
| AA-LCR | Not reported | |
| Agent Arena | $0.7652 / task Median Β· Net improvement index (percentage points vs. average model): 2.3 Thinking High (With Tools + Internet) | Not reported |
| Agent Arena Index | $0.7486 / task Median Β· Agent Arena Index rating (index points): 1118 Thinking High (With Tools + Internet) | Not reported |
| ARC-AGI-2 | $0.3997 / task Average Β· ARC-AGI-2 Score: 89.2 Thinking High (No Tools) $0.1545 / task Average Β· ARC-AGI-2 Score: 77.5 Thinking Low (No Tools) $0.2478 / task Average Β· ARC-AGI-2 Score: 82.9 Thinking Medium (No Tools) | Not reported |
| CursorBench 4.0 | $4.70 / task Average Β· Task score: 39.6 Thinking High (With Tools) Β· cursorbench-4-0-cursor-agent $4.06 / task Average Β· Task score: 37.3 Thinking Medium (With Tools) Β· cursorbench-4-0-cursor-agent | Not reported |
| DeepSWE | Not reported | |
| FrontierSWE v2 | Not reported | |
| Public Benefits Bench v1.1 | Not reported | $0.2245 / task Average Β· Criterion pass rate (%): 54.3 Unspecified Reasoning (With Tools) |
| Terminal-Bench 4.0 | $8.65 / task Average Β· Resolution rate (%): 19.7 Unspecified Reasoning (With Tools) Β· vals-mini-swe | Not reported |
| Terminal-Bench 4.1 | Not reported | |
| Vals Index v2.1 | Not reported | |
| Vals Index v2.2 | Not reported | |
| Vibe Code Bench 1-100 | Not reported | |
| WeirdML v3 | $3.9441 / task Average Β· Official score (0-1; higher is better): 0.074 Thinking High (With Tools) | Not reported |
| Attribute | Gemini 3.8 Flash | Haiku 4.5 |
|---|---|---|
| Availability | Available | Available |
| Provider | Google Deep Mind | Anthropic |
| Model type | Multimodal model | Multimodal model |
| First release | September 2, 2026 | October 15, 2025 |
| Context window | 1M tokens | 200K tokens |
| Max output | 64K tokens | 64K tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Reasoning, Coding, Function calling, Tool use, Structured output, Computer use, Web search, Long context | Reasoning, Multilingual |
| Input modalities | Text, Image, Audio, Video | Text, Image |
| Output modalities | Text | Text |
| Weights | Closed / API only | Closed / API only |
| Commercial use | Proprietary | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Gemini 3.8 Flash or Haiku 4.5? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.