claude-haiku-4-5-20251001_32K: benchmark scores, price and ranking

claude-haiku-4-5-20251001_32K from Anthropic ranks #442 of 743 LLMs on the LLMs Tiger aggregate benchmark score (47.3), based on 5 benchmark results captured up to 2026-10-13.

Organisation: Anthropic
Type: Fast / low-cost (flash) model
Open weights: No
Released: 2025-10-15 (source: curated)
Cheapest API price: $1.00 in / $5.00 out per million tokens (via anthropic, observed 2026-10-13T20:47Z)
Aggregate rank: #442 of 743 (score 47.3)

Relative to other models, claude-haiku-4-5-20251001_32K is strongest on OTIS Mock AIME (#85 of 189) and weakest on SimpleQA Verified (#65 of 69).

Across the 5 benchmarks where at least ten models are scored, claude-haiku-4-5-20251001_32K is in the top 10% on 0 and in the top half on 1.

Its cheapest listed input price, $1.00 per million tokens, is lower than that of 35% of the 427 models with a listed price.

claude-haiku-4-5-20251001_32K benchmark results

claude-haiku-4-5-20251001_32K benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
OTIS Mock AIME	66.7%	#85 of 189	Epoch AI Benchmarking Hub	2026-10-13
GPQA Diamond	71.2%	#141 of 275	Epoch AI Benchmarking Hub	2026-10-13
Chess Puzzles	8.0%	#68 of 122	Epoch AI Benchmarking Hub	2026-10-13
ALE-Bench	653	#49 of 79	Epoch AI Benchmarking Hub	2026-10-13
SimpleQA Verified	12.6%	#65 of 69	Epoch AI Benchmarking Hub	2026-10-13

About claude-haiku-4-5-20251001_32K

claude-haiku-4-5-20251001_32K is a smaller, lower-cost model from Anthropic. It was released on 2025-10-15, according to the developer's announcement. The cheapest API listing we track charges $1.00 per million input tokens and $5.00 per million output tokens, through anthropic. We hold 5 benchmark results for it across 3 areas, and none is in the top tenth of its board.

Where claude-haiku-4-5-20251001_32K stands

On our aggregate score, claude-haiku-4-5-20251001_32K is #442 of 743 ranked models, around the middle of the table. Its score is 47.3; the scale is centred on 50, so it sits 2.7 points below the typical model. That beats 41% of the ranked field. Among the 70 ranked Anthropic models it is #55. The next one up is Claude 3.7 at 47.4. The next one down is Claude Sonnet 3.5 at 46.7.

claude-haiku-4-5-20251001_32K, benchmark by benchmark

OTIS Mock AIME puts claude-haiku-4-5-20251001_32K at 66.7%, #85 of 189. That beats 55% of the models tested, but 33.3 points short of Claude Fable 5.1 (max) (100.0%). The results either side are Qwen3-32B (66.9%) and DeepSeek-R1 (May 2025) (66.4%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so claude-haiku-4-5-20251001_32K is 8.9 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

claude-haiku-4-5-20251001_32K lands below the middle on GPQA Diamond: 71.2%, #141 of 275, with 51% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is DeepSeek-R1 at 71.5%. It covers expert-level science questions. The board median is 71.7%, so claude-haiku-4-5-20251001_32K is 0.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

claude-haiku-4-5-20251001_32K lands below the middle on Chess Puzzles: 8.0%, #68 of 122, with 55% of the field scoring higher. GPT-6 Astra (max) leads at 72.0%; the closest result above is GLM-5 at 10.0%. It covers chess tactics puzzles. The board median is 12.5%, so claude-haiku-4-5-20251001_32K is 4.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

claude-haiku-4-5-20251001_32K lands below the middle on ALE-Bench: 653, #49 of 79, with 61% of the field scoring higher. GPT-6 Astra (max) leads at 2,951; the closest result above is claude-sonnet-4-20250514_32K at 655. It covers AtCoder heuristic-optimisation contests (performance rating). The board median is 764, so claude-haiku-4-5-20251001_32K is 110 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

SimpleQA Verified is a weak spot. claude-haiku-4-5-20251001_32K scores 12.6%, #65 of 69, behind 93% of the models measured. The leader, gemini-4-argon-high, reaches 76.0%. It covers short factual questions. The board median is 41.0%, so claude-haiku-4-5-20251001_32K is 28.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Reasoning, maths and science: solid, ahead of 52% of the field on average across 2 benchmarks. Its best board here is OTIS Mock AIME (#85 of 189) and its weakest is GPQA Diamond (#141 of 275). General knowledge and chat: weak, ahead of 25% of the field on average across 2 benchmarks. Its best board here is Chess Puzzles (#68 of 122) and its weakest is SimpleQA Verified (#65 of 69).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so claude-haiku-4-5-20251001_32K 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), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on o1-mini (high) ($1.10) and mimo-v2-pro ($1.10).

Release history

The Anthropic model released before it was claude-haiku-4-5-20251001 on 2025-10-15, which scores 45.2. The next one was Claude Haiku 4.5 (Thinking 32K) on 2025-10-15, at 47.7.

Reading these numbers

The 5 scores on this page come from 1 source: Epoch AI Benchmarking Hub (5). No official leaderboard supplied any of them, so treat them as third-party measurements. With 5 results the aggregate rank can move a lot when one new score arrives.