WizardLM-2-8x22B: benchmark scores, price and ranking

WizardLM-2-8x22B from Microsoft ranks #597 of 743 LLMs on the LLMs Tiger aggregate benchmark score (45.3), based on 2 benchmark results captured up to 2026-10-13.

Organisation: Microsoft
Type: Open-weight / local model
Open weights: Yes
Released: 2024-04-15 (source: epoch)
Context window: 65,535 tokens
Cheapest API price: $0.480 in / $0.480 out per million tokens (via deepinfra, observed 2026-10-13T21:47Z)
Aggregate rank: #597 of 743 (score 45.3)

Across the 2 benchmarks where at least ten models are scored, WizardLM-2-8x22B is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.480 per million tokens, is lower than that of 51% of the 427 models with a listed price.

WizardLM-2-8x22B benchmark results

WizardLM-2-8x22B benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
Aider Code Editing	44.4%	#68 of 92	Aider Aider Code Editing leaderboard	2026-10-13
GPQA Diamond	43.4%	#212 of 275	Epoch AI Benchmarking Hub	2026-10-13

About WizardLM-2-8x22B

WizardLM-2-8x22B is an open-weight model that can run on your own hardware from Microsoft. It was released on 2024-04-15, according to Epoch AI. It accepts up to 65,535 tokens of input at once. The cheapest API listing we track charges $0.480 per million input tokens and $0.480 per million output tokens, through deepinfra. We hold 2 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where WizardLM-2-8x22B stands

On our aggregate score, WizardLM-2-8x22B is #597 of 743 ranked models, in the lower half. Its score is 45.3; the scale is centred on 50, so it sits 4.7 points below the typical model. That beats 20% of the ranked field. Among the 3 ranked Microsoft models it is #2. The next one up is Phi-3-mini-4k-instruct at 46.2. The next one down is Phi-3-medium-128k-instruct at 44.0.

WizardLM-2-8x22B, benchmark by benchmark

WizardLM-2-8x22B lands below the middle on Aider Code Editing: 44.4%, #68 of 92, with 73% of the field scoring higher. Claude 3.5-Sonnet-20241022 leads at 84.2%; the closest result above is gemini-1.5-flash-latest at 44.4%. It covers Aider official benchmark. The board median is 55.6%, so WizardLM-2-8x22B is 11.2 points below it. Source: Aider Aider Code Editing leaderboard, captured 2026-10-13.

WizardLM-2-8x22B lands below the middle on GPQA Diamond: 43.4%, #212 of 275, with 77% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is Llama-3.1-70B-Instruct at 44.2%. It covers expert-level science questions. The board median is 71.7%, so WizardLM-2-8x22B is 28.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

WizardLM-2-8x22B 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 WizardLM-2-8x22B costs less 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 SWE-1.6 ($0.500) and GPT-3.5 Turbo (Nov 2023) ($0.500).

Release history

The next one was Phi-3-medium-128k-instruct on 2024-04-23, at 44.0.

Reading these numbers

The 2 scores on this page come from 2 sources: Aider Aider Code Editing leaderboard (1), Epoch AI Benchmarking Hub (1). 1 of them come from an official leaderboard and 1 from datasets or third-party runs. With 2 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#594 Qwen2.5-Coder-1.5B-Instruct (45.4)
#595 Llama 3.1-8B (45.3)
#596 Llama-2-13b-chat (45.3)
#598 c4ai-command-r7b-12-2024 (45.3)
#599 Nemotron 3 Super (45.3)
#600 Llama-2-70b-chat (45.3)