ModelRefs / Claude 3.5 Haiku vs Phi-4
Claude 3.5 Haiku vs Phi-4
Claude 3.5 Haiku vs Phi-4: side-by-side benchmarks, pricing, context windows, coding ability and deployment. Pick the right model for your stack.
Overview
Claude 3.5 Haiku: Claude 3.5 Haiku is Anthropic's fast, low-cost model from late 2024, built for high-volume work such as classification, extraction and routing across a 200,000-token context window. The claude-3-5-haiku-20241022 snapshot was deprecated on 19 December 2025 and retired on Anthropic-operated platforms on 19 February 2026, with Claude Haiku 4.5 named as its replacement.
Phi-4: Microsoft's 14B dense decoder-only open-weight text model, trained on 9.8T tokens with a synthetic-data-centered curriculum and available through the microsoft/phi-4 artifact and Microsoft Foundry.
Context window: Claude 3.5 Haiku accepts up to 200,000 tokens, Phi-4 up to 16,384. Confirm the limit for your specific deployment channel before relying on it.
Claude 3.5 Haiku vs Phi-4 at a glance
| Attribute | Claude 3.5 Haiku | Phi-4 |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Released | 2024-11-04 | 2024-12-12 |
| Context window | 200,000 tokens | 16,384 tokens |
| Input price | $0.8/M tokens | Free / self-hosted |
| Output price | $4/M tokens | Free / self-hosted |
| Licence | Proprietary | MIT |
| Self-hostable | No, hosted only | Yes, open weights |
| Modalities | text | text |
Benchmarks reported for both
| Benchmark | Claude 3.5 Haiku | Phi-4 | Reported |
|---|---|---|---|
| GPQA Diamond (accuracy) | 41.6 | 56.1 | 2024-12-12 |
Each row compares the same benchmark, the same reported metric, and the same task set. Scores are as published by their cited sources on the dates shown. Different runs still use different harnesses and prompts, so treat these as directional evidence rather than a head-to-head result.
Where they differ most
- Reasoning: Claude 3.5 Haiku 25%, Phi-4 61%. Phi-4 leads on this dimension.
- Cost Efficiency: Claude 3.5 Haiku 65%, Phi-4 100%. Phi-4 leads on this dimension.
Capability scores are ModelRefs' own derived signals, not vendor claims or benchmark results. Validate against your own workload before relying on them.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Claude 3.5 Haiku vs Phi-4.
Frequently asked questions
Which is better, Claude 3.5 Haiku or Phi-4?
Claude 3.5 Haiku and Phi-4 target different workloads — see the benchmark and pricing tables for a side-by-side answer.
Is Claude 3.5 Haiku cheaper than Phi-4?
Compare $0.00080 vs $0.00000 on this page.