Skip to content
Model Pareto

Compare models

Side by side: quality per category, price, speed, and every benchmark cell with where it came from. Pick up to four.
Claude Opus 5.5Granite 4.2 3BInkling Small
Focus

Coding: quality vs price

Compared models are ringed; the other 100 ranked here are greyed.

Lower price is better. Pareto frontier: Granite 4.2 3B, NVIDIA Nemotron 3 Nano 30B A3B, gpt-oss-20b, Ling-3.0-flash-VL, MiMo-V2.6-Flash, GLM-5.3 Flash, DeepSeek V4.1 Flash, MiMo-V2.6-Pro, Claude Sonnet 5.5, Claude Opus 5.5. 26 models are not plotted: Xing4.0-29B-A4B, Nex-N2.5-Pro, Atria Dawn Preview, Intern-S2-397B, Solar Open2 250B, Phi-4-reasoning-plus, Motif 3, Nex-N2-Pro, Nex-N2.5-Mini, A.X-K2, K2 Horizon 375B A23B, K-EXAONE 2.0 0803, K2 Horizon MoVA 36B A4B, Intern-S2-Preview (35B-A3B), Command A+, North Mini Code, G9v3-39A5B, Falcon-H1-34B-Instruct, Devstral 2, K2 Horizon 7B, Devstral Small 2, MiniCPM5-2B, Ling 3.0 Tiny, K2 Horizon 3.7B, K2 Horizon 0.9B, LFM2.5-2.6B.

26 models with no price data — shown in the strip at the left edge

Xing4.0-29B-A4B, Nex-N2.5-Pro, Atria Dawn Preview, Intern-S2-397B, Solar Open2 250B, Phi-4-reasoning-plus, Motif 3, Nex-N2-Pro, Nex-N2.5-Mini, A.X-K2, K2 Horizon 375B A23B, K-EXAONE 2.0 0803, K2 Horizon MoVA 36B A4B, Intern-S2-Preview (35B-A3B), Command A+, North Mini Code, G9v3-39A5B, Falcon-H1-34B-Instruct, Devstral 2, K2 Horizon 7B, Devstral Small 2, MiniCPM5-2B, Ling 3.0 Tiny, K2 Horizon 3.7B, K2 Horizon 0.9B, LFM2.5-2.6B

  • Best-value frontier (nothing is both cheaper and better)
  • Evidencestrong → weak
  • Estimated from other categories
  • Claude Opus 5.5
    Quality
    96.9
    Rank
    #1/103
    Price
    $8.00/M tok
    Speed
    92tok/s
    In$4.00Out$20/M tok

    vs Inkling Small: +52.9 quality · 15× price

  • Granite 4.2 3B
    Quality
    17.2
    Rank
    #95/103
    Price
    $0.05/M tok
    Speed
    220tok/s
    In$0.03▾Out$0.12▾/M tok

    vs Claude Opus 5.5: −79.6 quality · 0.01× price

  • Inkling Small
    Quality
    44.0
    Rank
    #38/103
    Price
    $0.52/M tok
    Speed
    206tok/s
    In$0.30Out$1.20/M tok

    vs Claude Opus 5.5: −52.9 quality · 0.07× price

Overview

Metric
Claude Opus 5.5
Granite 4.2 3B
Inkling Small
Lab
Anthropic
IBM Granite
Thinking Machines Lab
Released
Sep 22, 2026
Aug 25, 2026
Jul 30, 2026
Weights
Proprietary
Open
Open
Input price
$/M tok
$4.00
$0.03Best
$0.30
Output price
$/M tok
$20
$0.12Best
$1.20
Blended price
$/M tok · 3:1 in:out
$8.00
$0.052Best
$0.525
Output speed
tok/s
92
220Best
206
Context
tokens
1MBest
131K
1MBest

Quality by category

0–100 within each category (100 = best tracked model). Rank is among all models ranked there. Click a row to focus it.

Metric
Claude Opus 5.5
Granite 4.2 3B
Inkling Small
Coding
96.9±3.4Best
#1/103Mixedbest value
17.2±8.0
#95/103Verifiedbest value
44.0±8.0
#38/103Verified
Writing & chat
93.0±4.3
#3/146Verifiedbest value
Not ranked
Not ranked
Vision
94.5±4.8Best
#2/82Verifiedbest value
Not ranked
60.3±8.2
#30/82Verified
Hard reasoning
99.9±2.6Best
#1/182Verifiedbest value
23.4±3.7
#128/182Verified
68.6±5.8
#33/182Verified
Agents
99.6±4.1Best
#1/173Verifiedbest value
17.0±5.8
#140/173Verified
46.3±10.0
#45/173Verified

Coding benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Claude Opus 5.5
Granite 4.2 3B
Inkling Small
SWE-bench Verified
day 0
~#2/14~94.7%Estimated
  1. #1Claude Opus 596.0%
  2. ~#2Claude Opus 5.5Estimated94.7%
  3. #2Claude Sonnet 585.2%
estimated from related benchmarks
~#12/14~64.5%Estimated
  1. #1Claude Opus 596.0%
  2. #11Nemotron 3 Ultra70.7%
  3. ~#12Granite 4.2 3BEstimated64.5%
  4. #12Intern-S2-Preview (35B-A3B)64.0%
estimated from related benchmarks
~#5/14~78.2%Estimated
  1. #1Claude Opus 596.0%
  2. #4MiniMax-M380.5%
  3. ~#5Inkling SmallEstimated78.2%
  4. #5Hy378.0%
estimated from related benchmarks
SWE-bench Pro (Public)
day 0
#1/1889.9%Lab-reported
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
www-cdn.anthropic.com · 2026-09-22
~#18/19~45.9%Estimated
  1. #1Claude Opus 5.589.9%
  2. #17Muse Glimmer51.2%
  3. ~#18Granite 4.2 3BEstimated45.9%
  4. #18Nex-N2.5-Mini43.8%
estimated from related benchmarks
~#14/19~57.4%Estimated
  1. #1Claude Opus 5.589.9%
  2. #13Hy357.9%
  3. ~#14Inkling SmallEstimated57.4%
  4. #14Inkling54.3%
estimated from related benchmarks
DeepSWE v1.1
day 0
#8/3068.4%Verified
  1. #1DeepSeek V4.1 Flash74.2%
  2. #7GPT-6 Sol69.0%
  3. #8Claude Opus 5.568.4%
  4. #8Kimi K368.4%
artificialanalysis.ai · 2026-09-24
~#29/31~37.4%Estimated
  1. #1DeepSeek V4.1 Flash74.2%
  2. #28Qwen3.8 27B42.2%
  3. ~#29Granite 4.2 3BEstimated37.4%
  4. #29Nex-N2.5-Mini36.1%
estimated from related benchmarks
~#27/31~55.4%Estimated
  1. #1DeepSeek V4.1 Flash74.2%
  2. #26Nex-N2.5-Pro55.8%
  3. ~#27Inkling SmallEstimated55.4%
  4. #27Qwen3.8 Max (0902)51.0%
estimated from related benchmarks
Terminal-Bench 4.0
day 0
#2/8359.6%BestVerified
  1. #1Claude Sonnet 5.563.6%
  2. #2Claude Opus 5.559.6%
  3. #3GPT-6 Astra59.1%
artificialanalysis.ai · 2026-09-24
#49/830.0%Verified
  1. #1Claude Sonnet 5.563.6%
  2. #49gpt-oss-20b0.0%
  3. #49Granite 4.2 3B0.0%
  4. #49Granite 4.2 8B0.0%
artificialanalysis.ai · 2026-09-24
#32/831.0%Verified
  1. #1Claude Sonnet 5.563.6%
  2. #32Inkling1.0%
  3. #32Inkling Small1.0%
  4. #32K2 Horizon 7B1.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBench
third-party
~#2/20~92.3%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. ~#2Claude Opus 5.5Estimated92.3%
  3. #2Qwen3.8 Flash-Next91.9%
estimated from related benchmarks
~#14/20~40.8%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #13Devstral 244.8%
  3. ~#14Granite 4.2 3BEstimated40.8%
  4. #14Llama 4 Maverick39.7%
estimated from related benchmarks
~#6/20~82.5%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #5gpt-oss-120b87.8%
  3. ~#6Inkling SmallEstimated82.5%
  4. #6Gemma 4 31B80.0%
estimated from related benchmarks
SciCode
third-party
#1/9566.9%BestVerified
  1. #1Claude Opus 5.566.9%
  2. #2Claude Fable 5.163.1%
artificialanalysis.ai · 2026-09-24
#86/9525.3%Verified
  1. #1Claude Opus 5.566.9%
  2. #85MiniCPM5-2B26.3%
  3. #86Granite 4.2 3B25.3%
  4. #87Ling 3.0 Tiny24.2%
artificialanalysis.ai · 2026-09-24
#29/9549.7%Verified
  1. #1Claude Opus 5.566.9%
  2. #28Qwen3.8 Flash-Next50.6%
  3. #29Inkling Small49.7%
  4. #30Hy348.6%
artificialanalysis.ai · 2026-09-24
AA Coding Agent Index
third-party
#1/1466.0Verified
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
artificialanalysis.ai · 2026-09-24
~last/15below measured range (<41.1)Estimated
  1. #1Claude Opus 5.566.0
  2. #14GPT-6 Luna41.1
  3. ~#15Granite 4.2 3BEstimated<41.1
estimated from related benchmarks
~#14/15~41.3Estimated
  1. #1Claude Opus 5.566.0
  2. #13Gemini 3.8 Flash41.9
  3. ~#14Inkling SmallEstimated41.3
  4. #14GPT-6 Luna41.1
estimated from related benchmarks
Benchmarks in other categories (4)

Writing & chat benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Claude Opus 5.5
Granite 4.2 3B
Inkling Small

Vision benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Claude Opus 5.5
Granite 4.2 3B
Inkling Small
MMMU
day 0
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2Claude Opus 5.5Estimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
—
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2Inkling SmallEstimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
MMMU-Pro
day 0
#1/7687.7%BestVerified
  1. #1Claude Opus 5.587.7%
  2. #2GPT-6 Astra86.9%
artificialanalysis.ai · 2026-09-24
—
#33/7674.0%Verified
  1. #1Claude Opus 5.587.7%
  2. #32Muse Glimmer74.3%
  3. #33Inkling Small74.0%
  4. #34Inkling73.5%
artificialanalysis.ai · 2026-09-24
CharXiv Reasoning
day 0
~#2/9~86.1%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. ~#2Claude Opus 5.5Estimated86.1%
  3. #2Kimi K384.8%
estimated from related benchmarks
—
~#6/9~78.5%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. #5Muse Glimmer78.8%
  3. ~#6Inkling SmallEstimated78.5%
  4. #6Inkling78.1%
estimated from related benchmarks
OmniDocBench v1.5
third-party
~#2/8~91.4%Estimated
  1. #1MiniMax-M391.6%
  2. ~#2Claude Opus 5.5Estimated91.4%
  3. #2Kimi K391.1%
estimated from related benchmarks
—
~#5/8~85.1%Estimated
  1. #1MiniMax-M391.6%
  2. #4Gemini 3.1 Pro85.3%
  3. ~#5Inkling SmallEstimated85.1%
  4. #5Claude Haiku 4.579.6%
estimated from related benchmarks
GDP.pdf (AA)
third-party
#3/4226.2%Verified
  1. #1GPT-6 Astra31.0%
  2. #3Claude Fable 5.126.2%
  3. #3Claude Opus 5.526.2%
  4. #5GPT-6 Sol24.8%
artificialanalysis.ai · 2026-09-24
—
~#22/43~13.5%Estimated
  1. #1GPT-6 Astra31.0%
  2. #21Gemini 3.5 Flash-Lite13.6%
  3. ~#22Inkling SmallEstimated13.5%
  4. #22GPT-5.4 mini13.4%
estimated from related benchmarks
Chartography
third-party
#2/2266.3%Verified
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #3GPT-6 Sol53.6%
surgehq.ai · 2026-09-24
—
~#14/23~21.3%Estimated
  1. #1GPT-6 Astra71.0%
  2. #13Gemini 3.1 Pro26.1%
  3. ~#14Inkling SmallEstimated21.3%
  4. #14Grok 4.620.5%
estimated from related benchmarks

Hard reasoning benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Claude Opus 5.5
Granite 4.2 3B
Inkling Small
GPQA Diamond
day 0
~#2/173~96.1%Estimated
  1. #1GPT-6 Astra96.1%
  2. ~#2Claude Opus 5.5Estimated96.1%
  3. #2Gemini 3.8 Flash95.3%
estimated from related benchmarks
#124/17255.9%Verified
  1. #1GPT-6 Astra96.1%
  2. #123GLM-4.6V56.6%
  3. #124Granite 4.2 3B55.9%
  4. #125LFM2.5-2.6B55.8%
artificialanalysis.ai · 2026-09-24
#28/17289.5%BestVerified
  1. #1GPT-6 Astra96.1%
  2. #28Grok Build 0.1 061689.5%
  3. #28Inkling Small89.5%
  4. #30Qwen3.5 397B A17B89.3%
artificialanalysis.ai · 2026-09-24
Humanity's Last Exam
day 0
#1/17861.4%BestVerified
  1. #1Claude Opus 5.561.4%
  2. #2Claude Fable 5.159.1%
artificialanalysis.ai · 2026-09-24
#117/1786.6%Verified
  1. #1Claude Opus 5.561.4%
  2. #116LFM2.5-1.2B-Instruct6.7%
  3. #117Granite 4.2 3B6.6%
  4. #118MiniCPM5-1B6.5%
artificialanalysis.ai · 2026-09-24
#39/17833.3%Verified
  1. #1Claude Opus 5.561.4%
  2. #38Hy333.5%
  3. #39Inkling Small33.3%
  4. #40K2 Horizon 375B A23B32.0%
artificialanalysis.ai · 2026-09-24
AIME (latest)
day 0
~#2/25~96.7%Estimated
  1. #1Inkling97.1%
  2. ~#2Claude Opus 5.5Estimated96.7%
  3. #2Muse Glimmer94.7%
estimated from related benchmarks
~#14/25~44.1%Estimated
  1. #1Inkling97.1%
  2. #13Phi-4-reasoning-plus78.0%
  3. ~#14Granite 4.2 3BEstimated44.1%
  4. #14Mistral Large 338.0%
estimated from related benchmarks
~#2/25~95.4%Estimated
  1. #1Inkling97.1%
  2. ~#2Inkling SmallEstimated95.4%
  3. #2Muse Glimmer94.7%
estimated from related benchmarks
AA Intelligence Index
third-party
#1/7457.6BestVerified
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556.0
artificialanalysis.ai · 2026-09-24
#65/749.1Verified
  1. #1Claude Opus 5.557.6
  2. #64Qwen3 Coder Next9.2
  3. #65Granite 4.2 3B9.1
  4. #66gpt-oss-20b9.0
artificialanalysis.ai · 2026-09-24
~#26/75~30.6Estimated
  1. #1Claude Opus 5.557.6
  2. #25Qwen3.8 27B33.7
  3. ~#26Inkling SmallEstimated30.6
  4. #26K2 Horizon 375B A23B30.5
estimated from related benchmarks

Agents benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Claude Opus 5.5
Granite 4.2 3B
Inkling Small
τ²-bench (Telecom)
day 0
~#2/116~98.3%Estimated
  1. #1Step 3.7 Flash98.5%
  2. ~#2Claude Opus 5.5Estimated98.3%
  3. #2Gemini 3.1 Pro95.6%
estimated from related benchmarks
~#55/116~34.0%Estimated
  1. #1Step 3.7 Flash98.5%
  2. #54Sarvam 30B34.5%
  3. ~#55Granite 4.2 3BEstimated34.0%
  4. #55Gemma 4 12B31.9%
estimated from related benchmarks
~#16/116~89.1%Estimated
  1. #1Step 3.7 Flash98.5%
  2. #15KAT Coder Pro V289.5%
  3. ~#16Inkling SmallEstimated89.1%
  4. #16MiniMax-M388.9%
estimated from related benchmarks
OSWorld-Verified
day 0
~#2/12~84.6%Estimated
  1. #1Kimi K384.8%
  2. ~#2Claude Opus 5.5Estimated84.6%
  3. #2Qwen3.8 27B84.3%
estimated from related benchmarks
~#11/12~59.2%Estimated
  1. #1Kimi K384.8%
  2. #10Muse Glimmer65.9%
  3. ~#11Granite 4.2 3BEstimated59.2%
  4. #11Claude Haiku 4.550.7%
estimated from related benchmarks
~#10/12~69.7%Estimated
  1. #1Kimi K384.8%
  2. #9Nex-N2.5-Mini71.2%
  3. ~#10Inkling SmallEstimated69.7%
  4. #10Muse Glimmer65.9%
estimated from related benchmarks
OSWorld 2.0
day 0
~#2/5~58.7%Estimated
  1. #1GLM-5.3 Flash59.1%
  2. ~#2Claude Opus 5.5Estimated58.7%
  3. #2Kimi K358.3%
estimated from related benchmarks
~last/5below measured range (<47.5%)Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #4GPT-5.547.5%
  3. ~#5Granite 4.2 3BEstimated<47.5%
estimated from related benchmarks
~last/5below measured range (<47.5%)Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #4GPT-5.547.5%
  3. ~#5Inkling SmallEstimated<47.5%
estimated from related benchmarks
BrowseComp
day 0
~#2/18~92.3%Estimated
  1. #1Atria Dawn Preview92.5%
  2. ~#2Claude Opus 5.5Estimated92.3%
  3. #2GPT-6 Astra91.5%
estimated from related benchmarks
~#15/18~51.8%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #14Inkling77.1%
  3. ~#15Granite 4.2 3BEstimated51.8%
  4. #15Mistral Medium 3.548.6%
estimated from related benchmarks
~#15/18~67.3%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #14Inkling77.1%
  3. ~#15Inkling SmallEstimated67.3%
  4. #15Mistral Medium 3.548.6%
estimated from related benchmarks
GDPval-AA (Elo)
third-party
#1/861846BestVerified
  1. #1Claude Opus 5.51846
  2. #2Claude Fable 5.11735
artificialanalysis.ai · 2026-09-24
#84/86188Verified
  1. #1Claude Opus 5.51846
  2. #83Ministral 3 8B200
  3. #84Granite 4.2 3B188
  4. #85K2 Think V2117
artificialanalysis.ai · 2026-09-24
~#24/87~1367Estimated
  1. #1Claude Opus 5.51846
  2. #23GPT-6 Luna1367
  3. ~#24Inkling SmallEstimated1367
  4. #24K2 Horizon 375B A23B1349
estimated from related benchmarks
AutomationBench-AA
third-party
#1/7969.5%BestVerified
  1. #1Claude Opus 5.569.5%
  2. #2DeepSeek V4.1 Flash68.9%
artificialanalysis.ai · 2026-09-24
#72/790.4%Verified
  1. #1Claude Opus 5.569.5%
  2. #72Celeris-10.4%
  3. #72Granite 4.2 3B0.4%
  4. #74gpt-oss-120b0.2%
artificialanalysis.ai · 2026-09-24
~#32/80~24.9%Estimated
  1. #1Claude Opus 5.569.5%
  2. #31Gemini 3.5 Flash-Lite25.0%
  3. ~#32Inkling SmallEstimated24.9%
  4. #32Kimi K2.7 Code24.5%
estimated from related benchmarks
τ-Bench Banking (AA)
third-party
~#3/89~50.0%Estimated
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. ~#3Claude Opus 5.5Estimated50.0%
  4. #3Qwen3.8 2.4T A95B49.1%
estimated from related benchmarks
#76/885.6%Verified
  1. #1Muse Spark 1.350.5%
  2. #74Trinity Large Thinking5.8%
  3. #76Granite 4.2 3B5.6%
  4. #76HyperNova 60B 26055.6%
artificialanalysis.ai · 2026-09-24
#39/8818.8%BestVerified
  1. #1Muse Spark 1.350.5%
  2. #38K2 Horizon 3.7B19.6%
  3. #39Inkling Small18.8%
  4. #40Ring-2.6-1T17.9%
artificialanalysis.ai · 2026-09-24
Not comparable across labs (1)
OSWorld 2.0 (Sept 2026 release)
day 0
#1/381.8%Lab-reported
  1. #1Claude Opus 5.581.8%
  2. #2Claude Fable 5.180.7%
anthropic.com · 2026-09-22
—
—