Claude Haiku 4.5vs.Gemini 4 Carbon
Which one is better?
Only Gemini 4 Carbon has a place in the overall index so far; Claude Haiku 4.5 does not have enough benchmark results yet.
Claude Haiku 4.5
not ranked yet
Gemini 4 Carbon
Rank 1 to 5
Claude Haiku 4.5
fairly slow
Gemini 4 Carbon
fairly fast
Claude Haiku 4.5
fairly expensive
Gemini 4 Carbon
Claude Haiku 4.5
- Subscription
At Anthropic from €21.42 a month (Claude Pro). Through other providers from ≈ €6.36 a month (ElevenLabs Starter, with limited credits). 64 plans in Germany.
- Via API
$1 input, $5 output per 1M tokens, cheaper since Aug 22, 2026 (before $1.10 and $5.50).
- Note
- There is a successor: Claude Haiku 5.5 (rank 16 to 27, $0.10 input, $0.50 output).
Gemini 4 Carbon
- Subscription
Subscriptions in Germany: n/a
- Via API
n/a (no API price known).
Overall index with data through Oct 29, 2026 · Prices from Oct 29, 2026 · Speed: measured by Artificial Analysis · Subscriptions as of Oct 24, 2026 · Subscription prices incl. VAT
Where is the difference?
Values from 0 to 100 per task area. We only name a winner when the gap is large enough and there are enough tests.
Haiku 4.5 ahead: 0Gemini 4 Carbon ahead: 2level: 0too little data: 4of 6 areas
Show 1 more areas that do not count toward the overall index
See for yourself: same task, one attempt
The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.
Pelican on a bicycle
A community classic for free-form SVG drawing.
Claude Haiku 4.5
Reasoning (requested): high
Current attempt
- Run date
- Oct 1, 2026
- API provider
- openrouter
- Requested API model
- anthropic/claude-haiku-4.5
- API model reported in response
- anthropic/claude-haiku-4.5
- Reasoning setting
- high
- Pinned endpoint
- Anthropic | anthropic/claude-4.5-haiku-20251001
- Temperature
- Provider default
- Token limit including reasoning
- 8,192 tokens
- Test protocol
- community-visual-tests-v1
- Technical checks
- Passed, not a quality rating
- Response time
- 10.1 s
Visually reviewed. This individual test does not establish overall model quality.
Gemini 4 Carbon
Not tested yet
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)SVG short test
There is no shared test round for this selection. Results from different rounds are not mixed.
All data side by side
The better value is bold. For the overall index only when the gap is clear.
| Metric | Claude Haiku 4.5 | Gemini 4 Carbon |
|---|---|---|
| Intelligence | ||
| Overall index0 to 100, higher is better | n/a | 96 |
| Rank | not ranked yet | Rank 1 to 5 of 95 |
| Price per 1M tokens | ||
| Inputwhat you send | $1 | n/a |
| Outputwhat the model writes | $5 | n/a |
| Speed | ||
| Tokens per second | 86 | 100 |
| Technical | ||
| Context windowhow much text the model reads at once | 200,000 tokens≈ 300 A4 pages | 1 M tokens≈ 1,500 A4 pages |
| Knowledge cutoff | February 2025 | n/a |
| Released | October 2025 | n/a |
| Availability | Active | Limited access |
| Open weights | no | no |
- Gemini 4 Carbon, Announced introductory pricing: $2 input and $10 output per 1M tokens. Cached input receives a 95% discount, giving $0.10 per 1M tokens. This announcement does not establish an already available public API. Source
- Gemini 4 Carbon, Announced pricing after the introductory period: Afterward, $4 input and $20 output per 1M tokens. Google has not specified when the introductory period ends. Source
- Gemini 4 Carbon, Artificial Analysis pricing assumptions: Artificial Analysis calculates test costs using $4 input, $20 output, and $0.20 cached input per 1M tokens. These are the evaluator’s pricing assumptions, not confirmation of a publicly available API tariff. Source
Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis
Shared benchmarks
Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.
No directly comparable result yet
No published benchmark for Claude Haiku 4.5 and Gemini 4 Carbon currently matches in version, task and metric. We therefore show no estimated or blended values.
Compare another matchup
More matchups
Related LLM comparisons
Compare Claude Haiku 4.5 and Gemini 4 Carbon with other leading models.