Model comparison
Claude Haiku 4.5 vs Gemini 3.6 Flash
Anthropic against Google, compared on context, price, and verified benchmark results.
Catalog record checked August 14, 2026; individual provider fields may change.
Anthropic
Claude Haiku 4.5
Budget
Gemini 3.6 Flash
Budget
| Specification | Claude Haiku 4.5 | Gemini 3.6 Flash |
|---|---|---|
| Provider | Anthropic | |
| Tier | Budget | Budget |
| Context window | 200K | Winner: 1.05M |
| Max output | 64K | Winner: 66K |
| Input / 1M tokens | $1 | Winner: $0.75 |
| Output / 1M tokens | $5 | Winner: $3.75 |
| Weights | Closed | Closed |
| Parameters | Not disclosed | Not disclosed |
| Reasoning levels | Not verified | minimal, low, medium, high |
| Modalities | text, image | text, image, video, audio, pdf |
| Released | October 15, 2025 | July 21, 2026 |
| Artificial Analysis Intelligence Index [high] (2026-08-08) | 24 | Winner: 52 |
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.
Pricing tiers: Gemini 3.6 Flash: Introductory paid-tier rates through 2026-12-31. From 2027-01-01 the standard paid rates are $1.50 / $7.50 per million tokens (Gemini API pricing). Cache is $0.075 / MTok through 2026-12-31, then $0.15. Wire calls to `gemini-3.6-flash`. Thinking levels are `minimal` / `low` / `medium` / `high` (API default medium).
Claude Haiku 4.5
Anthropic's cheapest tier for high-volume classification and routine extraction.
Best for
- High-volume classification
- Routine extraction
- Cost-sensitive Anthropic stacks
Watch out
A generation behind the 5-series models it sits alongside in the lineup.
Gemini 3.6 Flash
Google's July 2026 Flash tier for multimodal volume work; 3.7 Flash is the newer coding/agent workhorse at the same introductory rate.
Best for
- Multimodal pipelines
- High-volume processing
- Video and audio input
Watch out
Introductory $0.75 input is 3.75× Luna; the $1.50 rate returns on 2027-01-01. 66K max output (65,536 tokens) is roughly half Luna's. Prefer 3.7 Flash for new coding-agent work unless you are pinned to 3.6.
Benchmark
DeepSWE 1.1 in context
Only Gemini 3.6 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
Claude Opus 5 [max]
74%
Rows shown
24
Highest published reasoning effort per model (not best Pass@1)
Snapshot date
2026-08-13
Mirrored from deepswe.datacurve.ai
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.
| # | Model | Pass@1 | Cost / task | Tokens / task | Steps / task |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 [max] | 74% | $11.84 | 118k | 99 |
| 2 | GPT-5.6 Sol [max] | 73% | $8.39 | 60k | 61 |
| 3 | Claude Fable 5 [max] | 70% | $21.63 | 119k | 88 |
| 4 | GPT-5.6 Terra [max] | 70% | $4.95 | 72k | 76 |
| 5 | Kimi K3 [max] | 69% | $4.65 | 82k | 98 |
| 6 | GPT-5.6 Luna [max] | 67% | $3.03 | 73k | 102 |
| 7 | GPT-5.5 [xhigh] | 67% | $7.23 | 46k | 82 |
| 8 | Grok 4.6 [xhigh] | 67% | $5.50 | 71k | 87 |
| 9 | Gemini 3.7 Flash [high] | 65% | $2.18 | 107k | 125 |
| 10 | DeepSeek V4-Pro [max] | 63% | $0.24 | 106k | 155 |
| 11 | Claude Opus 4.8 [max] | 59% | $13.22 | 135k | 120 |
| 12 | Qwen3.8-Max [xhigh] | 58% | $3.73 | 95k | 111 |
| 13 | Muse Spark 1.2 [xhigh] | 55% | $3.70 | 99k | 101 |
| 14 | Claude Sonnet 5 [max] | 54% | $26.40 | 214k | 268 |
| 15 | Grok 4.5 [high] | 54% | $2.42 | 36k | 61 |
| 16 | DeepSeek V4-Flash [max] | 53% | $0.10 | 108k | 153 |
| 17 | Muse Spark 1.1 [xhigh] | 53% | $2.36 | 74k | 96 |
| 18 | GPT-5.4 [xhigh] | 52% | $5.65 | 71k | 70 |
| 19 | Gemini 3.6 Flash [high] | 47% | $4.42 | 96k | 117 |
| 20 | GLM 5.2 [max] | 44% | $3.92 | 78k | 129 |
| 21 | Gemini 3.5 Flash [high] | 36% | $3.45 | 76k | 105 |
| 22 | Kimi K2.7 Code | 31% | $2.82 | 59k | 149 |
| 23 | Claude Sonnet 4.6 [high] | 30% | $5.52 | 76k | 134 |
| 24 | Gemini 3.1 Pro [high] | 12% | $2.14 | 28k | 76 |
DeepSWE “Best” picks the highest published reasoning effort per model (not the highest pass rate). Small gaps may not be statistically meaningful — confirm on deepswe.datacurve.ai.
Common questions
Claude Haiku 4.5 vs Gemini 3.6 Flash
Answered from the verified figures on this page rather than general guidance.
Is Claude Haiku 4.5 or Gemini 3.6 Flash cheaper for input?
Gemini 3.6 Flash is cheaper at $0.75 per million input tokens, against $1 for Claude Haiku 4.5 — roughly 1.3× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Gemini 3.6 Flash has tiered pricing: Introductory paid-tier rates through 2026-12-31. From 2027-01-01 the standard paid rates are $1.50 / $7.50 per million tokens (Gemini API pricing). Cache is $0.075 / MTok through 2026-12-31, then $0.15. Wire calls to `gemini-3.6-flash`. Thinking levels are `minimal` / `low` / `medium` / `high` (API default medium).
Is Claude Haiku 4.5 or Gemini 3.6 Flash cheaper for output?
Gemini 3.6 Flash is cheaper at $3.75 per million output tokens, against $5 for Claude Haiku 4.5 — roughly 1.3× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Gemini 3.6 Flash has tiered pricing: Introductory paid-tier rates through 2026-12-31. From 2027-01-01 the standard paid rates are $1.50 / $7.50 per million tokens (Gemini API pricing). Cache is $0.075 / MTok through 2026-12-31, then $0.15. Wire calls to `gemini-3.6-flash`. Thinking levels are `minimal` / `low` / `medium` / `high` (API default medium).
Which has the larger context window, Claude Haiku 4.5 or Gemini 3.6 Flash?
Gemini 3.6 Flash accepts 1.05M tokens against 200K for Claude Haiku 4.5. This only matters if you routinely send very long documents or large codebases.
Should I use Claude Haiku 4.5 or Gemini 3.6 Flash?
Both sit in the budget tier, so the choice usually comes down to price and context rather than capability. Claude Haiku 4.5 suits high-volume classification; Gemini 3.6 Flash suits multimodal pipelines.
Next step
Choosing between them
Tier and workload decide this more reliably than a leaderboard position does.
If both sit in the same tier, the decision usually comes down to context window and output price rather than headline capability — output tokens dominate real bills.
If one is a step up within the same provider, the useful question is whether your hardest task actually fails on the cheaper tier. Most production volume — classification, extraction, summarization — does not.
Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Muse Code, or Lovable? Compare agentic harnesses · Latest releases.