Model comparison
Claude Haiku 4.5 vs Gemini 3 Pro
Head-to-head evidence from 3 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Haiku 4.5 #77 (Estimated); Gemini 3 Pro #19 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Haiku 4.5 and Gemini 3 Pro share 3 comparable benchmark results. 1 of 8 categories are comparable. 2 results are unique to Claude Haiku 4.5; 24 to Gemini 3 Pro.
Updated July 22, 2026- Shared results
- 3
- Claude Haiku 4.5 only
- 2
- Gemini 3 Pro only
- 24
- Comparable categories
- 1 / 8
Pick Gemini 3 Pro if you want the stronger benchmark profile. Claude Haiku 4.5 only becomes the better choice if you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 3 shared benchmark results across 2 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Gemini 3 Pro is clearly ahead on the BenchAlign aggregate, 67.73 to 56.58. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Gemini 3 Pro's sharpest advantage is in mathematics, where it averages 32.9 against 4.9. The single biggest benchmark swing on the page is FrontierMath v2 (Tiers 1-3), 5.903% to 37.600%.
Gemini 3 Pro is also the more expensive model on tokens at $2.00 input / $12.00 output per 1M tokens, versus $1.00 input / $5.00 output per 1M tokens for Claude Haiku 4.5. That is roughly 2.4x on output cost alone. Gemini 3 Pro gives you the larger context window at 2M, compared with 200K for Claude Haiku 4.5.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Claude Haiku 4.5 | Δ | Gemini 3 Pro |
|---|---|---|---|
| Math | Claude Haiku 4.54.9 | Margin→ 28.0 | Gemini 3 Pro32.9 |
| Coding | Claude Haiku 4.573.3 | MarginNo overlap | Gemini 3 ProNot measured |
| Reasoning | Claude Haiku 4.5Not measured | MarginNo overlap | Gemini 3 Pro31.1 |
| Multimodal | Claude Haiku 4.5Not measured | MarginNo overlap | Gemini 3 Pro81.1 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
FrontierMath v2 (Tiers 1-3)
MathA 5.903%B 37.600%Winner: Gemini 3 ProΔ 31.7FrontierMath v2 (Tiers 1-3): Claude Haiku 4.5 scored 5.903%; Gemini 3 Pro scored 37.600%. Gemini 3 Pro wins this benchmark. - Source ↗
FrontierMath v2 (Tier 4)
MathA 2.083%B 18.750%Winner: Gemini 3 ProΔ 16.7FrontierMath v2 (Tier 4): Claude Haiku 4.5 scored 2.083%; Gemini 3 Pro scored 18.750%. Gemini 3 Pro wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude Haiku 4.5 | Gemini 3 Pro | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Haiku 4.5$1 input / $5 output | Gemini 3 Pro$2 input / $12 output | Claude Haiku 4.5 has the lower combined listed price. |
| Generation speedtokens per second | Claude Haiku 4.5Not available | Gemini 3 Pro109 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Claude Haiku 4.5Not available | Gemini 3 Pro32.65 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Claude Haiku 4.5200K | Gemini 3 Pro2M | Gemini 3 Pro lists the larger context window. |
Benchmark Deep Dive
Agentic3 benchmarks
Coding4 benchmarks
Reasoning3 benchmarks
Knowledge7 benchmarks
| Benchmark | Claude Haiku 4.5 | Gemini 3 Pro | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | — | 39.5% | Not comparable |
| AA-GPQA DiamondSource | — | 90.8% | Not comparable |
| AA-HLESource | — | 37.2% | Not comparable |
| AA-Omniscience IndexSource | — | 15.8% | Not comparable |
| AA-Omniscience AccuracySource | — | 55.9% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 90.9% | Not comparable |
| AA MMLU-ProSource | — | 89.8% | Not comparable |
MathGemini 3 Pro wins2 benchmarks
Multilingual1 benchmarks
| Benchmark | Claude Haiku 4.5 | Gemini 3 Pro | Result |
|---|---|---|---|
| AA Global-MMLU-LiteSource | — | 92.2% | Not comparable |
Multimodal8 benchmarks
| Benchmark | Claude Haiku 4.5 | Gemini 3 Pro | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1152 | — | Not comparable |
| MMMU-ProSource | — | 81% | Not comparable |
| MathVisionSource | — | 86.6% | Not comparable |
| VideoMMMUSource | — | 87.6% | Not comparable |
| ScreenSpot ProSource | — | 72.7% | Not comparable |
| CharXivSource | — | 81.4% | Not comparable |
| V*Source | — | 88.0% | Not comparable |
| AA-MMMU-ProSource | — | 80.2% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Claude Haiku 4.5 | Gemini 3 Pro | Result |
|---|---|---|---|
| AA-IFBenchSource | — | 70.4% | Not comparable |
Frequently Asked Questions (2)
Which is better, Claude Haiku 4.5 or Gemini 3 Pro?
Gemini 3 Pro is ahead on BenchLM's BenchAlign leaderboard, 67.73 to 56.58. The biggest single separator in this matchup is FrontierMath v2 (Tiers 1-3), where the scores are 5.903% and 37.600%.
Which is better for math, Claude Haiku 4.5 or Gemini 3 Pro?
Gemini 3 Pro has the edge for math in this comparison, averaging 32.9 versus 4.9. Inside this category, FrontierMath v2 (Tiers 1-3) is the benchmark that creates the most daylight between them.
Related Comparisons
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.