whichllmmodel
Back to Dashboard
Anthropic

Claude Haiku 4.5

VS
Google

Gemini 2.5 Pro

✍️ Analysis by:the whichllmmodel Editorial Team|📅 Updated: June 2026

Decision Recommendation

⚖️ Editorial Verdict: In our analysis, Claude Haiku 4.5 is the premium intelligence choice, scoring 39.5% higher on coding benchmarks. However, Gemini 2.5 Pro compensates by delivering 1.2x faster throughput. If you are building high-volume, simple chatbots or processing massive amounts of text where budget is critical, Gemini 2.5 Pro offers excellent cost savings. For agentic reasoning, code refactoring, or complex logical tasks, the accuracy premium of Claude Haiku 4.5 fully justifies the cost.

Model Specs

Claude Haiku 4.5

Benchmarks & Scores

Coding (swe-bench-pro)Winner (+)
39.5%
Reasoning (gpqa-diamond)
73%

Cost & Performance

Cost (per 1M tokens)1.7x cheaper
$2.00Input: $1.00 | Output: $5.00
Speed
98.5 tps
Context Window
200k tokens
Model Specs

Gemini 2.5 Pro

Benchmarks & Scores

Coding (swe-bench-pro)
N/A
Reasoning (gpqa-diamond)Winner (+11.4%)
84.4%

Cost & Performance

Cost (per 1M tokens)
$3.44Input: $1.25 | Output: $10.00
Speed1.2x faster
117 tps
Context WindowLarger
1M tokens
Read our data collection methodology

Frequently Asked Questions

Claude Haiku 4.5 is cheaper than Gemini 2.5 Pro. Claude Haiku 4.5 has a blended cost of $2.00/1M tokens, which is about 1.7x cheaper than Gemini 2.5 Pro at $3.44/1M tokens.

Gemini 2.5 Pro is faster than Claude Haiku 4.5. Gemini 2.5 Pro generates 117 tokens per second (tps) compared to Claude Haiku 4.5 which generates 98.5 tokens per second.

Claude Haiku 4.5 is better for coding tasks. It scores 39.5% on coding evaluations (swe-bench-pro) compared to Gemini 2.5 Pro which scores N/A.

Want to customize weights or add more models?

Open our interactive dashboard where you can adjust your priority levels for speed, budget, or accuracy slider-bars and watch model rankings calculate dynamically.

Customize in Interactive Dashboard