Claude Haiku 5.5 vs ERNIE 5.5 Flash Preview: Specs & Benchmark Comparison

Claude Haiku 5.5 is developed by Anthropic, while ERNIE 5.5 Flash Preview comes from Baidu. Claude Haiku 5.5 was released in October 2026, and ERNIE 5.5 Flash Preview followed a month later in November 2026. ERNIE 5.5 Flash Preview has a published size of about 280 billion parameters; Anthropic has not disclosed the parameter count of Claude Haiku 5.5.

The two models share 4 published benchmarks. ERNIE 5.5 Flash Preview leads on 4 of them. The widest gaps are on OfficeQA Pro, where ERNIE 5.5 Flash Preview scores 67.9% against 60.3%; Terminal-Bench 4.0, where ERNIE 5.5 Flash Preview scores 46.5% against 39.2%. Averaged across everything we track, Claude Haiku 5.5 sits at 57.7% and ERNIE 5.5 Flash Preview at 58.9%.

Claude Haiku 5.5 is the cheaper API at $0.10 per million input tokens and $0.50 per million output tokens, roughly 3 times cheaper than ERNIE 5.5 Flash Preview at $0.28 and $1.13. Both accept a context window of about 1M tokens. Claude Haiku 5.5 accepts text and images as input, while ERNIE 5.5 Flash Preview accepts text.

CharacteristicClaude Haiku 5.5ERNIE 5.5 Flash Preview
CompanyAnthropicBaidu
Release DateOctober 7, 2026November 11, 2026
Parameters—280B
MultimodalYesNo
Context (input)1.0M1.0M
Context (output)128K1.0M
Input Price / 1M$0.10$0.28
Output Price / 1M$0.50$1.13
Average Score57.7%58.9%
Benchmarks
OfficeQA Pro60.3%67.9%
Terminal-Bench 4.039.2%46.5%
Humanity's Last Exam (no tools, text-only)45.9%46.4%
Terminal-Bench-Science 0.120.6%21.0%

Visual Benchmark Comparison

Claude Haiku 5.5
ERNIE 5.5 Flash Preview
OfficeQA Pro0.6 vs 0.7
0.6
0.7
Terminal-Bench 4.00.4 vs 0.5
0.4
0.5
Humanity's Last Exam (no tools, text-only)0.5 vs 0.5
0.5
0.5
Terminal-Bench-Science 0.10.2 vs 0.2
0.2
0.2

Verdict

Both models show equal results — the choice depends on your specific use case.

Overall Performance

Both models show comparable average scores: Claude Haiku 5.5 — 0.6, ERNIE 5.5 Flash Preview — 0.6.

API Cost

Claude Haiku 5.5 is 2.4x cheaper: input $0.10/1M vs $0.28/1M tokens.

Context Window

Same context size: 1M tokens.

Recency

ERNIE 5.5 Flash Preview is newer: released 11/11/2026 vs 10/7/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — Claude Haiku 5.5 or ERNIE 5.5 Flash Preview?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — Claude Haiku 5.5 or ERNIE 5.5 Flash Preview?
Claude Haiku 5.5 is cheaper for input: $0.10 per 1M tokens vs $0.28.
Which has a larger context window — Claude Haiku 5.5 or ERNIE 5.5 Flash Preview?
Claude Haiku 5.5 supports a larger context: 1,048,576 tokens vs 1,048,576.

The Claude Haiku 5.5 and ERNIE 5.5 Flash Preview comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Claude Haiku 5.5 or ERNIE 5.5 Flash Preview page. See also the complete list of AI model comparisons.