CoreWeave: Models Intelligence, Performance & Price

CoreWeave
CoreWeave

This analysis is intended to support you in choosing the best model provided by CoreWeave for your use-case.

Most Intelligent

#1
DeepSeek V4.1 Flash 1017 (max)DeepSeek V4.1 Flash 1017 (max)
33
#2
GLM-5.3-FlashGLM-5.3-Flash
28
#3
Qwen3.8 27B (xhigh) (FP8)Qwen3.8 27B (xhigh) (FP8)
20
#4
MiniMax-M3 (NVFP4)MiniMax-M3 (NVFP4)
19
#5
DeepSeek V4.1 Flash 1017 (non-reasoning)DeepSeek V4.1 Flash 1017 (non-reasoning)
19

Intelligence Index

Total 32 models

Lowest Time per Task

#1
Beam 1.0 (NVFP4)Beam 1.0 (NVFP4)
2.3 min
#2
Nemotron 3 UltraNemotron 3 Ultra
2.9 min
#3
Nemotron 3.5 Super VL (NVFP4)Nemotron 3.5 Super VL (NVFP4)
2.9 min
#4
Nemotron 3.5 Lightning (BF16)Nemotron 3.5 Lightning (BF16)
4.0 min
#5
DeepSeek V4.1 Flash 1017 (non-reasoning)DeepSeek V4.1 Flash 1017 (non-reasoning)
4.5 min

Time per Intelligence Index task (minutes)

Total 32 models

Lowest Price

#1
Granite 4.2 8BGranite 4.2 8B
$0.04
#2
gpt-oss-20b (low)gpt-oss-20b (low)
$0.04
#3
gpt-oss-20b (high)gpt-oss-20b (high)
$0.04
#4
gpt-oss-120b (high)gpt-oss-120b (high)
$0.04
#5
gpt-oss-120b (low)gpt-oss-120b (low)
$0.04

Blended price (per 1M tokens)

Total 32 models

CoreWeave offers 32 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.

  • For intelligence, the top models on CoreWeave are DeepSeek V4.1 Flash 1017 (max) (33), GLM-5.3-Flash (28), and Qwen3.8 27B (xhigh) (FP8) (20).
  • For time per task, Beam 1.0 (NVFP4) (2.3 min), Nemotron 3 Ultra (2.9 min), and Nemotron 3.5 Super VL (NVFP4) (2.9 min) finish an Intelligence Index task fastest on CoreWeave.
  • For latency, DeepSeek V4.1 Flash 1017 (non-reasoning) (0.89s), DeepSeek V4.1 Flash (non-reasoning) (0.90s), and DeepSeek V4 Pro (non-reasoning) (1.14s) offer the lowest time to first answer token.
  • For pricing, Granite 4.2 8B ($0.04), gpt-oss-20b (low) ($0.04), and gpt-oss-20b (high) ($0.04) offer the lowest blended prices per 1M tokens.
  • For context window size, Beam 1.0 (NVFP4) (1M), DeepSeek V4.1 Flash 1017 (max) (1M), and GLM-5.3-Flash (1M) support the largest context windows on CoreWeave.
Artificial Analysis Intelligence Index · Higher is better
Inference time (minutes) per Intelligence Index task · Lower is better
USD per 1M tokens (blended) · Lower is better

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Evaluations

Evaluations measured independently by Artificial Analysis · AA-PersonalityBench scores are percentile ranks from 1 to 100
See more

Agentic knowledge work, Elo

Agentic SaaS workflows

Agentic scientific research workflows in a terminal

Agentic software engineering in open-source repositories

Reasoning & knowledge

Professional document reasoning, All-pass

Agentic coding & terminal use

Physics reasoning

Quantitative analysis on spreadsheets & documents

Legal agentic work, Hallucination-Gated All-Pass Rate

Agentic business operations

Agentic real-world work tasks, Elo

Agentic interactive 3D experiences, Elo

Product and brand videos designed in code, Elo

Kubernetes incident root-cause analysis

Medical long context reasoning

Visual reasoning

Rich, varied, well-crafted language

Well-structured, scannable, answer-first

Truthful, acknowledges uncertainty, non-sycophantic

Use of filler and generic language

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

Pricing

Cost per Intelligence Index Task

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

Speed

Average of the single-request and multi-turn agentic workloads measured

Time per Intelligence Index Task

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Lower is better

Quality

Endpoint Accuracy Index

Each endpoint's accuracy as a % of its model's reference endpoint · Color shows whether the gap is statistically significant

Latency

Average of the single-request and multi-turn agentic workloads measured

Time to First Answer Token

Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better

Reliability

Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

Endpoint Error Rate

Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better

Caching

Cache Hit Rate

Median across multi-turn agentic session runs in the last four weeks, updated Oct 26, 2026 · Higher is better

Cost per Task vs. Cache Hit Rate

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026
Most attractive quadrant
Pareto line

Further Analysis
DeepSeek logo
DeepSeek V4.1 Flash 1017 (max)
33
$2.37
8.8
28.81
0.7%
1M
Open
Z AI logo
GLM-5.3-Flash
28
$0.53
12.9
34.41
2.5%
1M
Open
Alibaba logo
Qwen3.8 27B (xhigh) (FP8)
20
$3.30
26.5
150.19
2.2%
262k
Open
MiniMax logo
MiniMax-M3 (NVFP4)
19
$1.48
6.6
6.77
0.0%
262k
Open
DeepSeek logo
DeepSeek V4.1 Flash 1017 (non-reasoning)
19
$2.09
4.4
0.85
0.0%
1M
Open
Reflection logo
Beam 1.0 (NVFP4)
18
$0.70
2.1
6.92
0.0%
1M
Open
NVIDIA logo
Nemotron 3.5 Super VL (NVFP4)
14
$0.47
3.2
9.63
0.0%
1M
Open
NVIDIA logo
Nemotron 3 Ultra
12
$3.16
2.8
2.20
0.0%
262k
Open
NVIDIA logo
Nemotron 3.5 Lightning (BF16)
6
$0.24
4.1
12.68
0.0%
262k
Open
IBM logo
Granite 4.2 8B
5
$0.0387
9.1
34.13
0.0%
131k
Open
Google logo
Gemma 4 31B
4
--
--
7.06
1.3%
262k
Open
OpenAI logo
gpt-oss-120b (high)
4
$0.0727
12.3
20.78
13.5%
131k
Open
Kimi logo
Kimi K2.6
--
--
--
32.78
0.0%
262k
Open
Kimi logo
Kimi K2.6 (non-reasoning)
--
--
--
2.17
0.0%
262k
Open
OpenAI logo
gpt-oss-20b (low)
--
--
--
1.99
1.5%
131k
Open
OpenAI logo
gpt-oss-20b (high)
--
--
--
44.36
1.7%
131k
Open
Z AI logo
GLM-5 (FP8)
--
--
--
--
--
200k
Open
Alibaba logo
Qwen3.6 35B A3B (non-reasoning) (FP8)
--
--
--
2.32
0.0%
262k
Open
Google logo
Gemma 4 26B A4B
--
--
--
28.30
2.2%
262k
Open
DeepSeek logo
DeepSeek V4 Pro (non-reasoning)
--
--
--
1.25
0.0%
1M
Open
Google logo
Gemma 4 26B A4B (non-reasoning)
--
--
--
3.35
0.7%
262k
Open
Meta logo
Llama 3.1 8B
--
--
--
1.41
4.0%
128k
Open
DeepSeek logo
DeepSeek V4.1 Flash (non-reasoning)
--
--
--
0.88
0.0%
1M
Open
Alibaba logo
Qwen3.6 35B A3B (FP8)
--
--
--
20.60
0.0%
262k
Open
Kimi logo
Kimi K2.7 Code
--
--
--
60.62
4.2%
262k
Open
Meta logo
Llama 3.3 70B
--
--
--
1.70
0.0%
128k
Open
DeepSeek logo
DeepSeek V4 Pro (max)
--
--
--
34.03
0.0%
1M
Open
OpenAI logo
gpt-oss-120b (low)
--
--
--
3.71
1.5%
131k
Open
Google logo
Gemma 4 31B (non-reasoning)
--
--
--
6.83
0.7%
262k
Open
DeepSeek logo
DeepSeek V4.1 Flash (max)
--
--
--
36.09
4.3%
1M
Open
Z AI logo
GLM-5.2 (max)
--
--
--
11.63
0.0%
262k
Open
DeepSeek logo
DeepSeek V3.1 (non-reasoning)
--
--
--
2.08
0.0%
128k
Open
DeepSeek logo
DeepSeek V4 Flash 0731 (max)
--
--
--
36.46
0.0%
262k
Open

Key definitions

Frequently Asked Questions

Common questions about CoreWeave