Claude 3.5 Haiku: benchmark scores, price and ranking

Claude 3.5 Haiku from Anthropic ranks #346 of 743 LLMs on the LLMs Tiger aggregate benchmark score (48.5), based on 2 benchmark results captured up to 2026-10-13.

Organisation: Anthropic
Type: Fast / low-cost (flash) model
Open weights: No
Released: 2024-10-22 (source: curated)
Cheapest API price: $0.800 in / $4.00 out per million tokens (via vercel_ai_gateway, observed 2026-10-13T20:47Z)
Aggregate rank: #346 of 743 (score 48.5)

Across the 2 benchmarks where at least ten models are scored, Claude 3.5 Haiku is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.800 per million tokens, is lower than that of 38% of the 427 models with a listed price.

Claude 3.5 Haiku benchmark results

Claude 3.5 Haiku benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
Epoch ECI	127	#104 of 204	Epoch AI Benchmarking Hub	2026-10-13
SWE-bench Verified	40.6%	#53 of 73	SWE-bench Verified leaderboard	2026-10-13

About Claude 3.5 Haiku

Claude 3.5 Haiku is a smaller, lower-cost model from Anthropic. It was released on 2024-10-22, according to the developer's announcement. The cheapest API listing we track charges $0.800 per million input tokens and $4.00 per million output tokens, through vercel_ai_gateway. We hold 2 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where Claude 3.5 Haiku stands

On our aggregate score, Claude 3.5 Haiku is #346 of 743 ranked models, around the middle of the table. Its score is 48.5; the scale is centred on 50, so it sits 1.5 points below the typical model. That beats 53% of the ranked field. Among the 70 ranked Anthropic models it is #51. The next one up is Claude Opus 4 at 48.9. The next one down is claude-3-7-sonnet-20250219 at 48.2.

Claude 3.5 Haiku, benchmark by benchmark

Claude 3.5 Haiku lands below the middle on Epoch ECI: 127, #104 of 204, with 50% of the field scoring higher. Qwen 3.8 Max leads at 156; the closest result above is GPT-4 Turbo (Apr 2024) at 127. It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so Claude 3.5 Haiku is 0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Claude 3.5 Haiku lands below the middle on SWE-bench Verified: 40.6%, #53 of 73, with 71% of the field scoring higher. Claude Opus 4.7 (max) leads at 83.5%; the closest result above is Llama3-SWE-RL-70B at 41.2%. It covers real GitHub issues resolved. The board median is 56.4%, so Claude 3.5 Haiku is 15.8 points below it. Source: SWE-bench Verified leaderboard, captured 2026-10-13.

Strengths and weaknesses

Claude 3.5 Haiku has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Claude 3.5 Haiku costs more than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), DeepSeek V4 Flash 0731 (max) ($0.016, 53.1). Similar scores cost more on Llama-3.1-Nemotron-70B-Instruct-HF ($0.880) and Inkling (xhigh) ($0.950).

Release history

The Anthropic model released before it was Claude Sonnet 3.5 on 2024-06-20, which scores 46.7. The next one was claude-3-5-haiku-20241022 on 2024-10-22, at 50.8.

Reading these numbers

The 2 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (1), SWE-bench Verified leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#343 QwQ-32B + Qwen 2.5 Coder Instruct (48.5)
#344 Codex + GPT-5.6 Terra (48.5)
#345 Tencent-Hunyuan-Large (48.5)
#347 Mellum2-12B-A2.5B-Thinking (48.5)
#348 Qwen3.8-27B (XHigh) (48.5)
#349 SWE-agent-LM-32B (48.5)