Model comparison
Claude 3.5 Sonnet vs Claude 3 Haiku
Head-to-head evidence from 0 shared benchmark results across 0 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude 3.5 Sonnet #132 (Estimated); Claude 3 Haiku #194 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude 3.5 Sonnet and Claude 3 Haiku share 0 comparable benchmark results. 0 of 8 categories are comparable. 4 results are unique to Claude 3.5 Sonnet; 12 to Claude 3 Haiku.
Updated July 21, 2026- Shared results
- 0
- Claude 3.5 Sonnet only
- 4
- Claude 3 Haiku only
- 12
- Comparable categories
- 0 / 8
Benchmark data for Claude 3.5 Sonnet and Claude 3 Haiku is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 0 shared benchmark results across 0 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
Claude 3.5 Sonnet is priced at $3.00 input / $15.00 output per 1M tokens, versus $0.25 input / $1.25 output per 1M tokens for Claude 3 Haiku.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude 3.5 Sonnet | Claude 3 Haiku | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude 3.5 Sonnet$3 input / $15 output | Claude 3 Haiku$0.25 input / $1.25 output | Claude 3 Haiku has the lower combined listed price. |
| Generation speedtokens per second | Claude 3.5 SonnetNot available | Claude 3 Haiku138 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Claude 3.5 SonnetNot available | Claude 3 Haiku1.16 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Claude 3.5 Sonnet200K | Claude 3 Haiku200K | Listed context windows are equal. |
Benchmark Deep Dive
Agentic1 benchmarks
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku | Result |
|---|---|---|---|
| τ²-bench resultsSource | — | 21.1% | Not comparable |
Coding2 benchmarks
Reasoning2 benchmarks
Knowledge7 benchmarks
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku | Result |
|---|---|---|---|
| GPQASource | 59.4% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 3.9% | Not comparable |
| AA-GPQA DiamondSource | — | 37.4% | Not comparable |
| AA-HLESource | — | 3.9% | Not comparable |
| AA-Omniscience IndexSource | — | -47.6% | Not comparable |
| AA-Omniscience AccuracySource | — | 17.2% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 78.2% | Not comparable |
Math2 benchmarks
Multimodal1 benchmarks
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku | Result |
|---|---|---|---|
| AA-MMMU-ProSource | — | 30.8% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku | Result |
|---|---|---|---|
| AA-IFBenchSource | — | 36.1% | Not comparable |
Frequently Asked Questions (3)
Can I compare Claude 3.5 Sonnet and Claude 3 Haiku on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for Claude 3.5 Sonnet and Claude 3 Haiku today?
Claude 3.5 Sonnet: $3.00 input / $15.00 output per 1M tokens Claude 3 Haiku: $0.25 input / $1.25 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
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.