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.
Grok 4.6MiMo-V2.6-ProQwen3.8 2.4T A95B
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
  • Grok 4.6
    Quality
    59.0
    Rank
    #25/103
    Price
    $3.00/M tok
    Speed
    60tok/s
    In$2.00Out$6.00/M tok

    vs MiMo-V2.6-Pro: −18.8 quality · 5.5× price

  • MiMo-V2.6-Pro
    Quality
    77.8
    Rank
    #7/103
    Price
    $0.54/M tok
    Speed
    49tok/s
    In$0.435▾Out$0.87▾/M tok

    vs Grok 4.6: +18.8 quality · 0.18× price

  • Qwen3.8 2.4T A95B
    Quality
    55.6
    Rank
    #28/103
    Price
    $3.00/M tok
    Speed
    38tok/s
    In$2.00Out$6.00/M tok

    vs MiMo-V2.6-Pro: −22.2 quality · 5.5× price

Overview

Metric
Grok 4.6
MiMo-V2.6-Pro
Qwen3.8 2.4T A95B
Lab
SpaceXAI (xAI)
Xiaomi MiMo
Alibaba Qwen
Released
Aug 12, 2026
Sep 21, 2026
Aug 12, 2026
Weights
Proprietary
Open
Open
Input price
$/M tok
$2.00
$0.435Best
$2.00
Output price
$/M tok
$6.00
$0.87Best
$6.00
Blended price
$/M tok · 3:1 in:out
$3.00
$0.544Best
$3.00
Output speed
tok/s
60Best
49
38
Context
tokens
500K
1MBest
262K

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
Grok 4.6
MiMo-V2.6-Pro
Qwen3.8 2.4T A95B
Coding
59.0±4.5
#25/103Verified
77.9±6.4Best
#7/103Mixedbest value
55.6±6.4
#28/103Mixed
Writing & chat
72.0±6.0
#22/146Verified
81.8±6.0Best
#11/146Verifiedbest value
73.2±7.3
#20/146Mixed
Vision
65.2±7.3
#21/82Verified
76.5±9.4Best
#12/82Verified
Not ranked
Hard reasoning
82.2±3.7
#12/182Verified
86.1±5.1Best
#7/182Verifiedbest value
78.8±3.7
#19/182Verified
Agents
84.1±5.8
#10/173Verified
84.4±6.4Best
#9/173Mixed
83.0±5.8
#11/173Verified

Coding benchmarks

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

Metric
Grok 4.6
MiMo-V2.6-Pro
Qwen3.8 2.4T A95B
SWE-bench Verified
day 0
~#3/14~82.8%Estimated
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. ~#3Grok 4.6Estimated82.8%
  4. #3Gemini 3.1 Pro80.6%
estimated from related benchmarks
~#2/14~89.6%Estimated
  1. #1Claude Opus 596.0%
  2. ~#2MiMo-V2.6-ProEstimated89.6%
  3. #2Claude Sonnet 585.2%
estimated from related benchmarks
~#3/14~82.4%Estimated
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. ~#3Qwen3.8 2.4T A95BEstimated82.4%
  4. #3Gemini 3.1 Pro80.6%
estimated from related benchmarks
SWE-bench Pro (Public)
day 0
~#7/19~64.1%Estimated
  1. #1Claude Opus 5.589.9%
  2. #6Hy4 preview65.7%
  3. ~#7Grok 4.6Estimated64.1%
  4. #7GPT-5.6 Terra63.4%
estimated from related benchmarks
~#5/19~71.8%Estimated
  1. #1Claude Opus 5.589.9%
  2. #4Claude Opus 579.2%
  3. ~#5MiMo-V2.6-ProEstimated71.8%
  4. #5Intern-S2-397B68.5%
estimated from related benchmarks
~#9/19~63.0%Estimated
  1. #1Claude Opus 5.589.9%
  2. #8Claude Sonnet 563.2%
  3. ~#9Qwen3.8 2.4T A95BEstimated63.0%
  4. #9Nex-N2.5-Pro61.2%
estimated from related benchmarks
DeepSWE v1.1
day 0
#15/3064.9%Verified
  1. #1DeepSeek V4.1 Flash74.2%
  2. #14Gemini 3.8 Flash65.8%
  3. #15Grok 4.664.9%
  4. #16Claude Fable 5.164.3%
artificialanalysis.ai · 2026-09-24
#3/3071.9%BestLab-reported
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #3MiMo-V2.6-Pro71.9%
  4. #4Muse Spark 1.371.7%
huggingface.co · 2026-09-21
#25/3056.6%Lab-reported
  1. #1DeepSeek V4.1 Flash74.2%
  2. #24DeepSeek V4 Pro (0813)57.2%
  3. #25Qwen3.8 2.4T A95B56.6%
  4. #26Nex-N2.5-Pro55.8%
huggingface.co · 2026-08-12
Terminal-Bench 4.0
day 0
#19/8317.2%Verified
  1. #1Claude Sonnet 5.563.6%
  2. #18Gemini 3.8 Flash19.7%
  3. #19Grok 4.617.2%
  4. #20GPT-5.514.6%
artificialanalysis.ai · 2026-09-24
#10/8334.8%BestVerified
  1. #1Claude Sonnet 5.563.6%
  2. #9GPT-5.6 Terra35.4%
  3. #10MiMo-V2.6-Pro34.8%
  4. #11Muse Spark 1.333.3%
artificialanalysis.ai · 2026-09-24
#26/8311.1%Verified
  1. #1Claude Sonnet 5.563.6%
  2. #23Kimi K312.6%
  3. #26Qwen3.8 2.4T A95B11.1%
  4. #27Qwen3.8 27B5.6%
artificialanalysis.ai · 2026-09-24
LiveCodeBench
third-party
~#3/20~90.8%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. ~#3Grok 4.6Estimated90.8%
  4. #3Qwen3.8 27B90.3%
estimated from related benchmarks
~#2/20~92.1%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. ~#2MiMo-V2.6-ProEstimated92.1%
  3. #2Qwen3.8 Flash-Next91.9%
estimated from related benchmarks
~#4/20~89.4%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #3Qwen3.8 27B90.3%
  3. ~#4Qwen3.8 2.4T A95BEstimated89.4%
  4. #4Nemotron 3 Ultra89.0%
estimated from related benchmarks
SciCode
third-party
#20/9553.0%Verified
  1. #1Claude Opus 5.566.9%
  2. #19Qwen3.8 2.4T A95B54.1%
  3. #20Grok 4.653.0%
  4. #21GPT-5.5 Instant (June 2026)52.5%
artificialanalysis.ai · 2026-09-24
#4/9560.9%BestVerified
  1. #1Claude Opus 5.566.9%
  2. #3Claude Sonnet 5.561.0%
  3. #4MiMo-V2.6-Pro60.9%
  4. #5Kimi K359.5%
artificialanalysis.ai · 2026-09-24
#19/9554.1%Verified
  1. #1Claude Opus 5.566.9%
  2. #18Claude Sonnet 554.3%
  3. #19Qwen3.8 2.4T A95B54.1%
  4. #20Grok 4.653.0%
artificialanalysis.ai · 2026-09-24
AA Coding Agent Index
third-party
#10/1447.0Verified
  1. #1Claude Opus 5.566.0
  2. #9Kimi K351.9
  3. #10Grok 4.647.0
  4. #11Qwen3.8 Max (0902)43.3
artificialanalysis.ai · 2026-09-24
~#7/15~55.0Estimated
  1. #1Claude Opus 5.566.0
  2. #6Grok 4.756.3
  3. ~#7MiMo-V2.6-ProEstimated55.0
  4. #7Muse Spark 1.354.3
estimated from related benchmarks
~#11/15~46.8Estimated
  1. #1Claude Opus 5.566.0
  2. #10Grok 4.647.0
  3. ~#11Qwen3.8 2.4T A95BEstimated46.8
  4. #11Qwen3.8 Max (0902)43.3
estimated from related benchmarks
Not comparable across labs (1)
SWE-bench Pro (Qwen-corrected)
day 0
—
—
#1/467.7%Lab-reported
  1. #1Qwen3.8 2.4T A95B67.7%
  2. #2Qwen3.8-Omni-Flash63.3%
huggingface.co · 2026-08-12
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
Grok 4.6
MiMo-V2.6-Pro
Qwen3.8 2.4T A95B
IFBench
day 0
~#20/126~74.7%Estimated
  1. #1MiniMax-M382.9%
  2. #19GPT-5.3 Codex75.4%
  3. ~#20Grok 4.6Estimated74.7%
  4. #20Command A+73.9%
estimated from related benchmarks
~#4/126~81.5%Estimated
  1. #1MiniMax-M382.9%
  2. #3Qwen3.8-Omni-Flash81.5%
  3. ~#4MiMo-V2.6-ProEstimated81.5%
  4. #4Nemotron 3 Ultra81.4%
estimated from related benchmarks
#2/12582.8%Lab-reported
  1. #1MiniMax-M382.9%
  2. #2Qwen3.8 2.4T A95B82.8%
  3. #3Qwen3.8-Omni-Flash81.5%
huggingface.co · 2026-08-12
MMMLU
day 0
~#2/5~89.6%Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Grok 4.6Estimated89.6%
  3. #2Gemma 4 31B88.4%
estimated from related benchmarks
~#2/5~90.9%Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2MiMo-V2.6-ProEstimated90.9%
  3. #2Gemma 4 31B88.4%
estimated from related benchmarks
~#2/5~91.3%Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Qwen3.8 2.4T A95BEstimated91.3%
  3. #2Gemma 4 31B88.4%
estimated from related benchmarks
LMArena Text, Non-English (Elo)
third-party
#18/531447Verified
  1. #1Claude Opus 5.51501
  2. #18Claude Sonnet 51447
  3. #18Grok 4.61447
  4. #20Gemini 3.5 Flash-Lite1445
lmarena.ai · 2026-09-24
#13/531461BestVerified
  1. #1Claude Opus 5.51501
  2. #12DeepSeek V4.1 Flash1462
  3. #13MiMo-V2.6-Pro1461
  4. #14GPT-6 AstraFew votes1460
lmarena.ai · 2026-09-25
~#16/54~1449Estimated
  1. #1Claude Opus 5.51501
  2. #15GPT-5.6 Terra1456
  3. ~#16Qwen3.8 2.4T A95BEstimated1449
  4. #16DeepSeek V4 Pro (0813)1448
estimated from related benchmarks
LMArena Text (Elo)
third-party
#22/531453Verified
  1. #1Claude Opus 5.51509
  2. #19Qwen3.7 Plus1456
  3. #22Grok 4.61453
  4. #23Gemma 4 31B1451
lmarena.ai · 2026-09-25
#10/531480BestVerified
  1. #1Claude Opus 5.51509
  2. #10GPT-6 AstraFew votes1480
  3. #10MiMo-V2.6-Pro1480
  4. #13DeepSeek V4.1 Flash1477
lmarena.ai · 2026-09-25
~#18/54~1460Estimated
  1. #1Claude Opus 5.51509
  2. #17Claude Sonnet 51461
  3. ~#18Qwen3.8 2.4T A95BEstimated1460
  4. #18GPT-6 Sol1457
estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)
third-party
~#10/26~1897Estimated
  1. #1GPT-6 Astra2173
  2. #9Muse Spark 1.31906
  3. ~#10Grok 4.6Estimated1897
  4. #10GPT-5.6 Terra1855
estimated from related benchmarks
~#9/26~1966Estimated
  1. #1GPT-6 Astra2173
  2. #8Grok 4.72007
  3. ~#9MiMo-V2.6-ProEstimated1966
  4. #9Muse Spark 1.31906
estimated from related benchmarks
#12/251843Verified
  1. #1GPT-6 Astra2173
  2. #11GPT-5.51844
  3. #12Qwen3.8 2.4T A95B1843
  4. #13Muse Glimmer1798
eqbench.com · 2026-09-24

Vision benchmarks

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

Metric
Grok 4.6
MiMo-V2.6-Pro
Qwen3.8 2.4T A95B
MMMU
day 0
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2Grok 4.6Estimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2MiMo-V2.6-ProEstimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
—
MMMU-Pro
day 0
~#10/77~81.5%Estimated
  1. #1Claude Opus 5.587.7%
  2. #9Intern-S2-397B81.7%
  3. ~#10Grok 4.6Estimated81.5%
  4. #10GPT-5.6 Terra80.7%
estimated from related benchmarks
~#4/77~85.3%Estimated
  1. #1Claude Opus 5.587.7%
  2. #3Gemini 3.8 Flash85.6%
  3. ~#4MiMo-V2.6-ProEstimated85.3%
  4. #4Claude Opus 584.7%
estimated from related benchmarks
—
CharXiv Reasoning
day 0
~#5/9~81.8%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. #4Qwen3.8-Omni-Flash83.5%
  3. ~#5Grok 4.6Estimated81.8%
  4. #5Muse Glimmer78.8%
estimated from related benchmarks
~#4/9~84.1%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. #3Qwen3.8 Flash-Next84.6%
  3. ~#4MiMo-V2.6-ProEstimated84.1%
  4. #4Qwen3.8-Omni-Flash83.5%
estimated from related benchmarks
—
OmniDocBench v1.5
third-party
~#4/8~88.2%Estimated
  1. #1MiniMax-M391.6%
  2. #2Qwen3.8 27B91.1%
  3. ~#4Grok 4.6Estimated88.2%
  4. #4Gemini 3.1 Pro85.3%
estimated from related benchmarks
~#4/8~90.1%Estimated
  1. #1MiniMax-M391.6%
  2. #2Qwen3.8 27B91.1%
  3. ~#4MiMo-V2.6-ProEstimated90.1%
  4. #4Gemini 3.1 Pro85.3%
estimated from related benchmarks
—
GDP.pdf (AA)
third-party
#16/4217.2%Verified
  1. #1GPT-6 Astra31.0%
  2. #15Gemini 3.1 Pro17.8%
  3. #16Grok 4.617.2%
  4. #17Qwen3.8 27B16.6%
artificialanalysis.ai · 2026-09-24
#14/4219.2%BestVerified
  1. #1GPT-6 Astra31.0%
  2. #13Grok 4.720.0%
  3. #14MiMo-V2.6-Pro19.2%
  4. #15Gemini 3.1 Pro17.8%
artificialanalysis.ai · 2026-09-24
—
Chartography
third-party
#14/2220.5%Verified
  1. #1GPT-6 Astra71.0%
  2. #13Gemini 3.1 Pro26.1%
  3. #14Grok 4.620.5%
  4. #15Muse Glimmer17.2%
surgehq.ai · 2026-09-24
~#7/23~32.0%Estimated
  1. #1GPT-6 Astra71.0%
  2. #6GPT-5.6 Terra34.0%
  3. ~#7MiMo-V2.6-ProEstimated32.0%
  4. #7GPT-5.531.0%
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
Grok 4.6
MiMo-V2.6-Pro
Qwen3.8 2.4T A95B
GPQA Diamond
day 0
#5/17293.5%BestVerified
  1. #1GPT-6 Astra96.1%
  2. #5GPT-5.593.5%
  3. #5Grok 4.693.5%
  4. #5Kimi K393.5%
artificialanalysis.ai · 2026-09-24
~#2/173~95.5%Estimated
  1. #1GPT-6 Astra96.1%
  2. ~#2MiMo-V2.6-ProEstimated95.5%
  3. #2Gemini 3.8 Flash95.3%
estimated from related benchmarks
#5/17293.5%BestVerified
  1. #1GPT-6 Astra96.1%
  2. #5Muse Spark 1.393.5%
  3. #5Qwen3.8 2.4T A95B93.5%
  4. #5Step 5 Preview93.5%
artificialanalysis.ai · 2026-09-24
Humanity's Last Exam
day 0
#14/17844.1%Verified
  1. #1Claude Opus 5.561.4%
  2. #13GPT-5.545.8%
  3. #14Grok 4.644.1%
  4. #15Hy4 preview43.4%
artificialanalysis.ai · 2026-09-24
#6/17849.4%BestVerified
  1. #1Claude Opus 5.561.4%
  2. #5GPT-6 Astra54.7%
  3. #6MiMo-V2.6-Pro49.4%
  4. #7Muse Spark 1.348.7%
artificialanalysis.ai · 2026-09-24
#20/17842.4%Verified
  1. #1Claude Opus 5.561.4%
  2. #19GPT-5.3 Codex42.5%
  3. #20Qwen3.8 2.4T A95B42.4%
  4. #21GLM-5.342.3%
artificialanalysis.ai · 2026-09-24
AIME (latest)
day 0
~#2/25~96.8%Estimated
  1. #1Inkling97.1%
  2. ~#2Grok 4.6Estimated96.8%
  3. #2Muse Glimmer94.7%
estimated from related benchmarks
~#2/25~96.5%Estimated
  1. #1Inkling97.1%
  2. ~#2MiMo-V2.6-ProEstimated96.5%
  3. #2Muse Glimmer94.7%
estimated from related benchmarks
~#2/25~96.7%Estimated
  1. #1Inkling97.1%
  2. ~#2Qwen3.8 2.4T A95BEstimated96.7%
  3. #2Muse Glimmer94.7%
estimated from related benchmarks
AA Intelligence Index
third-party
#12/7444.2Verified
  1. #1Claude Opus 5.557.6
  2. #11GLM-5.344.8
  3. #12Grok 4.644.2
  4. #13Step 5 Preview43.7
artificialanalysis.ai · 2026-09-24
#9/7446.3BestVerified
  1. #1Claude Opus 5.557.6
  2. #8Grok 4.746.4
  3. #9MiMo-V2.6-Pro46.3
  4. #10Qwen3.8 Max (0902)45.4
artificialanalysis.ai · 2026-09-24
#18/7439.9Verified
  1. #1Claude Opus 5.557.6
  2. #17Gemini 3.8 Flash40.9
  3. #18Qwen3.8 2.4T A95B39.9
  4. #19Qwen3.8 Flash-Next39.8
artificialanalysis.ai · 2026-09-24

Agents benchmarks

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

Metric
Grok 4.6
MiMo-V2.6-Pro
Qwen3.8 2.4T A95B
τ²-bench (Telecom)
day 0
~#2/116~97.7%Estimated
  1. #1Step 3.7 Flash98.5%
  2. ~#2Grok 4.6Estimated97.7%
  3. #2Gemini 3.1 Pro95.6%
estimated from related benchmarks
~#2/116~98.1%Estimated
  1. #1Step 3.7 Flash98.5%
  2. ~#2MiMo-V2.6-ProEstimated98.1%
  3. #2Gemini 3.1 Pro95.6%
estimated from related benchmarks
~#2/116~98.3%Estimated
  1. #1Step 3.7 Flash98.5%
  2. ~#2Qwen3.8 2.4T A95BEstimated98.3%
  3. #2Gemini 3.1 Pro95.6%
estimated from related benchmarks
OSWorld-Verified
day 0
~#3/12~82.4%Estimated
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. ~#3Grok 4.6Estimated82.4%
  4. #3Nex-N2.5-Pro82.2%
estimated from related benchmarks
#4/1182.0%Lab-reported
  1. #1Kimi K384.8%
  2. #3Nex-N2.5-Pro82.2%
  3. #4MiMo-V2.6-Pro82.0%
  4. #5Claude Sonnet 581.2%
huggingface.co · 2026-09-21
~#3/12~83.1%Estimated
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. ~#3Qwen3.8 2.4T A95BEstimated83.1%
  4. #3Nex-N2.5-Pro82.2%
estimated from related benchmarks
OSWorld 2.0
day 0
~#3/5~56.6%Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Grok 4.6Estimated56.6%
  4. #3GPT-5.6 Terra50.2%
estimated from related benchmarks
~#3/5~56.9%Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3MiMo-V2.6-ProEstimated56.9%
  4. #3GPT-5.6 Terra50.2%
estimated from related benchmarks
~#3/5~57.3%Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Qwen3.8 2.4T A95BEstimated57.3%
  4. #3GPT-5.6 Terra50.2%
estimated from related benchmarks
BrowseComp
day 0
~#6/18~89.6%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #5Nex-N2.5-Pro89.7%
  3. ~#6Grok 4.6Estimated89.6%
  4. #6Step 5 Preview88.7%
estimated from related benchmarks
~#5/18~90.7%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #4Claude Opus 590.8%
  3. ~#5MiMo-V2.6-ProEstimated90.7%
  4. #5Nex-N2.5-Pro89.7%
estimated from related benchmarks
~#5/18~89.9%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #4Claude Opus 590.8%
  3. ~#5Qwen3.8 2.4T A95BEstimated89.9%
  4. #5Nex-N2.5-Pro89.7%
estimated from related benchmarks
GDPval-AA (Elo)
third-party
#10/861632Verified
  1. #1Claude Opus 5.51846
  2. #9GLM-5.3 Flash1641
  3. #10Grok 4.61632
  4. #11Qwen3.8 Flash-Next1612
artificialanalysis.ai · 2026-09-24
#6/861673BestVerified
  1. #1Claude Opus 5.51846
  2. #5Muse Spark 1.31674
  3. #6MiMo-V2.6-Pro1673
  4. #7Qwen3.8 Max (0902)1668
artificialanalysis.ai · 2026-09-24
#13/861597Verified
  1. #1Claude Opus 5.51846
  2. #12DeepSeek V4.1 Flash1600
  3. #13Qwen3.8 2.4T A95B1597
  4. #14Step 5 Preview1566
artificialanalysis.ai · 2026-09-24
AutomationBench-AA
third-party
#4/7967.0%BestVerified
  1. #1Claude Opus 5.569.5%
  2. #3GPT-6 Astra68.5%
  3. #4Grok 4.667.0%
  4. #5Grok 4.765.6%
artificialanalysis.ai · 2026-09-24
#12/7958.6%Verified
  1. #1Claude Opus 5.569.5%
  2. #11Claude Fable 5.159.4%
  3. #12MiMo-V2.6-Pro58.6%
  4. #13Kimi K358.3%
artificialanalysis.ai · 2026-09-24
#15/7957.2%Verified
  1. #1Claude Opus 5.569.5%
  2. #14Muse Spark 1.357.9%
  3. #15Qwen3.8 2.4T A95B57.2%
  4. #16DeepSeek V4 Pro (0813)56.7%
artificialanalysis.ai · 2026-09-24
τ-Bench Banking (AA)
third-party
#11/8843.3%Verified
  1. #1Muse Spark 1.350.5%
  2. #10Gemini 3.8 Flash44.9%
  3. #11Grok 4.643.3%
  4. #12Claude Opus 542.1%
artificialanalysis.ai · 2026-09-24
~#11/89~44.5%Estimated
  1. #1Muse Spark 1.350.5%
  2. #10Gemini 3.8 Flash44.9%
  3. ~#11MiMo-V2.6-ProEstimated44.5%
  4. #11Grok 4.643.3%
estimated from related benchmarks
#3/8849.1%BestVerified
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #3Qwen3.8 2.4T A95B49.1%
  4. #4Qwen3.8 27B48.0%
artificialanalysis.ai · 2026-09-24