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 Haiku 5.5Gemini 3.8 FlashMuse Spark 1.3
Focus

Coding: quality vs price

Compared models are ringed; the other 116 ranked here are greyed.

Lower price is better. Pareto frontier: Nex-N2.5-Mini, Nex-N2.5-Pro, MiMo-V2.6-Flash, Ternary Bonsai 2 27B, MiMo-V2.6-Pro, Gemini 4 Argon, Claude Opus 5.5. 34 models are not plotted: GLM-5.3 Flash NVFP4, DeepSeek V4.1 Flash NVFP4, GLM-5.3 NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, Xing4.0-29B-A4B, Ternary Bonsai 27B, Atria Dawn Preview, Maple-Preview, Bonsai 27B, Qwen3.8 27B NVFP4, Intern-S2-397B, Phi-4-reasoning-plus, Solar Open2 250B, Laguna S 2.1, Motif 3, Nex-N2-Pro, K-EXAONE 2.0 0803, K2 Horizon 375B A23B, A.X-K2, K2 Horizon MoVA 36B A4B, Intern-S2-Preview (35B-A3B), North Mini Code, G9v3-39A5B, Falcon-H1-34B-Instruct, Qwen3.8 Flash-Next NVFP4, Devstral 2, K2 Horizon 7B, K2-Horizon-32B, Devstral Small 2, MiniCPM5-2B, Ling 3.0 Tiny, K2 Horizon 3.7B, K2 Horizon 0.9B, LFM2.5-2.6B.

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

GLM-5.3 Flash NVFP4, DeepSeek V4.1 Flash NVFP4, GLM-5.3 NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, Xing4.0-29B-A4B, Ternary Bonsai 27B, Atria Dawn Preview, Maple-Preview, Bonsai 27B, Qwen3.8 27B NVFP4, Intern-S2-397B, Phi-4-reasoning-plus, Solar Open2 250B, Laguna S 2.1, Motif 3, Nex-N2-Pro, K-EXAONE 2.0 0803, K2 Horizon 375B A23B, A.X-K2, K2 Horizon MoVA 36B A4B, Intern-S2-Preview (35B-A3B), North Mini Code, G9v3-39A5B, Falcon-H1-34B-Instruct, Qwen3.8 Flash-Next NVFP4, Devstral 2, K2 Horizon 7B, K2-Horizon-32B, 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 Haiku 5.5
    Quality
    66.2
    Rank
    #19/119
    Price
    $0.20/M tok
    Speed
    —
    In$0.10▾Out$0.50▾/M tok

    vs Muse Spark 1.3: −6.4 quality · 0.1× price

  • Gemini 3.8 Flash
    Quality
    55.4
    Rank
    #37/119
    Price
    $1.50/M tok
    Speed
    129tok/s
    In$0.75Out$3.75/M tok

    vs Muse Spark 1.3: −17.2 quality · 0.75× price

  • Muse Spark 1.3
    Quality
    72.6
    Rank
    #11/119
    Price
    $2.00/M tok
    Speed
    209tok/s
    In$1.25Out$4.25/M tok

    vs Claude Haiku 5.5: +6.4 quality · 10× price

Overview

Metric
Claude Haiku 5.5
Gemini 3.8 Flash
Muse Spark 1.3
Lab
Anthropic
Google DeepMind
Meta
Released
Oct 7, 2026
Sep 2, 2026
Sep 2, 2026
Weights
Proprietary
Proprietary
Proprietary
Input price
$/M tok
$0.10Best
$0.75
$1.25
Output price
$/M tok
$0.50Best
$3.75
$4.25
Blended price
$/M tok · 3:1 in:out
$0.20Best
$1.50
$2.00
Output speed
tok/s
—
129
209Best
Context
tokens
1MBest
1MBest
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 Haiku 5.5
Gemini 3.8 Flash
Muse Spark 1.3
Coding
66.2±8.0
#19/119Verified
55.4±4.5
#37/119Verified
72.6±4.5Best
#11/119Verified
Writing & chat
Not ranked
73.5±4.6
#22/156Verified
78.6±4.6Best
#10/156Verifiedbest value
Vision
78.7±9.7
#7/91Lab-reportedbest value
82.1±4.1Best
#6/91Mixedbest value
78.4±4.8
#8/91Verified
Hard reasoning
81.3±5.1
#17/200Verifiedbest value
82.6±3.7
#13/200Verified
86.9±3.7Best
#8/200Verifiedbest value
Agents
Not ranked
75.8±5.8
#18/178Verified
87.0±5.8Best
#4/178Verifiedbest value

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 Haiku 5.5
Gemini 3.8 Flash
Muse Spark 1.3
SWE-bench Verified
day 0
~#2/14~86.8%Estimated
  1. #1Claude Opus 596.0%
  2. ~#2Claude Haiku 5.5Estimated86.8%
  3. #2Claude Sonnet 585.2%
estimated from related benchmarks
~#3/14~84.7%Estimated
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. ~#3Gemini 3.8 FlashEstimated84.7%
  4. #3Gemini 3.1 Pro80.6%
estimated from related benchmarks
~#2/14~88.2%Estimated
  1. #1Claude Opus 596.0%
  2. ~#2Muse Spark 1.3Estimated88.2%
  3. #2Claude Sonnet 585.2%
estimated from related benchmarks
SWE-bench Pro (Public)
day 0
~#6/20~68.1%Estimated
  1. #1Claude Opus 5.589.9%
  2. #5Intern-S2-397B68.5%
  3. ~#6Claude Haiku 5.5Estimated68.1%
  4. #6Hy4 preview65.7%
estimated from related benchmarks
~#6/20~65.7%Estimated
  1. #1Claude Opus 5.589.9%
  2. #5Intern-S2-397B68.5%
  3. ~#6Gemini 3.8 FlashEstimated65.7%
  4. #6Hy4 preview65.7%
estimated from related benchmarks
~#5/20~70.5%Estimated
  1. #1Claude Opus 5.589.9%
  2. #4Claude Opus 579.2%
  3. ~#5Muse Spark 1.3Estimated70.5%
  4. #5Intern-S2-397B68.5%
estimated from related benchmarks
DeepSWE v1.1
day 0
~#22/35~63.2%Estimated
  1. #1Gemini 4 Argon78.8%
  2. #21GLM-5.3 Flash63.4%
  3. ~#22Claude Haiku 5.5Estimated63.2%
  4. #22Claude Opus 562.5%
estimated from related benchmarks
#16/3465.8%Verified
  1. #1Gemini 4 Argon78.8%
  2. #15GPT-5.567.0%
  3. #16Gemini 3.8 Flash65.8%
  4. #17Grok 4.664.9%
artificialanalysis.ai · 2026-09-24
#6/3471.7%BestVerified
  1. #1Gemini 4 Argon78.8%
  2. #5MiMo-V2.6-Pro71.9%
  3. #6Muse Spark 1.371.7%
  4. #7Claude Sonnet 5.571.0%
artificialanalysis.ai · 2026-09-24
Terminal-Bench 4.0
day 0
#15/8832.8%Verified
  1. #1Claude Sonnet 5.563.6%
  2. #13Step 5 Preview33.3%
  3. #15Claude Haiku 5.532.8%
  4. #15GLM-5.3 Flash32.8%
artificialanalysis.ai · 2026-10-07
#22/8819.7%Verified
  1. #1Claude Sonnet 5.563.6%
  2. #21MiMo-V2.6-Flash22.7%
  3. #22Gemini 3.8 Flash19.7%
  4. #23Grok 4.617.2%
artificialanalysis.ai · 2026-09-24
#13/8833.3%BestVerified
  1. #1Claude Sonnet 5.563.6%
  2. #12MiMo-V2.6-Pro34.8%
  3. #13Muse Spark 1.333.3%
  4. #13Step 5 Preview33.3%
artificialanalysis.ai · 2026-09-24
LiveCodeBench
third-party
~#7/25~84.4%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #6gpt-oss-120b87.8%
  3. ~#7Claude Haiku 5.5Estimated84.4%
  4. #7Ternary Bonsai 27B82.8%
estimated from related benchmarks
~#7/25~83.6%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #6gpt-oss-120b87.8%
  3. ~#7Gemini 3.8 FlashEstimated83.6%
  4. #7Ternary Bonsai 27B82.8%
estimated from related benchmarks
~#7/25~86.9%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #6gpt-oss-120b87.8%
  3. ~#7Muse Spark 1.3Estimated86.9%
  4. #7Ternary Bonsai 27B82.8%
estimated from related benchmarks
SciCode
third-party
#21/10555.0%Verified
  1. #1Claude Opus 5.566.9%
  2. #20GPT-6.1 Sol55.7%
  3. #21Claude Haiku 5.555.0%
  4. #21GPT-5.6 Terra55.0%
artificialanalysis.ai · 2026-10-07
#15/10556.6%Verified
  1. #1Claude Opus 5.566.9%
  2. #14Grok 4.757.4%
  3. #15Gemini 3.8 Flash56.6%
  4. #16GPT-6 Astra56.5%
artificialanalysis.ai · 2026-09-24
#9/10558.8%BestVerified
  1. #1Claude Opus 5.566.9%
  2. #8Step 5 Preview58.9%
  3. #9Muse Spark 1.358.8%
  4. #10Gemini 3.1 Pro58.7%
artificialanalysis.ai · 2026-09-24
AA Coding Agent Index
third-party
~#12/18~50.9Estimated
  1. #1Claude Opus 5.566.0
  2. #11Kimi K351.9
  3. ~#12Claude Haiku 5.5Estimated50.9
  4. #12Mistral Large 449.8
estimated from related benchmarks
#16/1741.9Verified
  1. #1Claude Opus 5.566.0
  2. #15DeepSeek V4 Pro (0813)43.1
  3. #16Gemini 3.8 Flash41.9
  4. #17GPT-6 Luna41.1
artificialanalysis.ai · 2026-09-24
#9/1754.3BestVerified
  1. #1Claude Opus 5.566.0
  2. #8Grok 4.756.3
  3. #9Muse Spark 1.354.3
  4. #10GLM-5.353.6
artificialanalysis.ai · 2026-09-24
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 Haiku 5.5
Gemini 3.8 Flash
Muse Spark 1.3
IFBench
day 0
—
~#15/134~77.9%Estimated
  1. #1MiniMax-M382.9%
  2. #14Qwen3.7 Plus78.0%
  3. ~#15Gemini 3.8 FlashEstimated77.9%
  4. #15DeepSeek V4.1 Flash NVFP477.3%
estimated from related benchmarks
~#9/134~80.2%Estimated
  1. #1MiniMax-M382.9%
  2. #8Nemotron Cascade 2 30B A3B80.4%
  3. ~#9Muse Spark 1.3Estimated80.2%
  4. #9Inkling79.8%
estimated from related benchmarks
MMMLU
day 0
—
~#2/5~92.0%Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Gemini 3.8 FlashEstimated92.0%
  3. #2Gemma 4 31B88.4%
estimated from related benchmarks
~#2/5~92.1%Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Muse Spark 1.3Estimated92.1%
  3. #2Gemma 4 31B88.4%
estimated from related benchmarks
LMArena Text, Non-English (Elo)
third-party
—
#5/561483VerifiedFew votes
  1. #1Gemini 4 ArgonFew votes1512
  2. #5Claude Opus 51483
  3. #5Gemini 3.8 FlashFew votes1483
  4. #7Gemini 3.1 Pro1480
lmarena.ai · 2026-09-25
#4/561487BestVerifiedFew votes
  1. #1Gemini 4 ArgonFew votes1512
  2. #3Claude Opus 5.51494
  3. #4Muse Spark 1.3Few votes1487
  4. #5Claude Opus 51483
lmarena.ai · 2026-09-25
LMArena Text (Elo)
third-party
—
#4/561493BestVerified
  1. #1Gemini 4 Argon1525
  2. #3Claude Fable 5.11501
  3. #4Gemini 3.8 Flash1493
  4. #4Muse Spark 1.31493
lmarena.ai · 2026-09-24
#4/561493BestVerified
  1. #1Gemini 4 Argon1525
  2. #4Gemini 3.8 Flash1493
  3. #4Muse Spark 1.31493
  4. #6Claude Opus 51490
lmarena.ai · 2026-09-24
EQ-Bench Creative Writing v3 (Elo)
third-party
—
#15/251748Verified
  1. #1GPT-6 Astra2173
  2. #14Claude Sonnet 51794
  3. #15Gemini 3.8 Flash1748
  4. #16Nemotron 3 Ultra1692
eqbench.com · 2026-09-24
#9/251906BestVerified
  1. #1GPT-6 Astra2173
  2. #8Grok 4.72007
  3. #9Muse Spark 1.31906
  4. #10GPT-5.6 Terra1855
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
Claude Haiku 5.5
Gemini 3.8 Flash
Muse Spark 1.3
MMMU
day 0
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2Claude Haiku 5.5Estimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2Gemini 3.8 FlashEstimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2Muse Spark 1.3Estimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
MMMU-Pro
day 0
~#18/86~79.1%Estimated
  1. #1Claude Opus 5.587.7%
  2. #17Apodex 1.179.2%
  3. ~#18Claude Haiku 5.5Estimated79.1%
  4. #18Gemini 3.5 Flash-Lite79.0%
estimated from related benchmarks
#4/8585.6%BestVerified
  1. #1Claude Opus 5.587.7%
  2. #3GPT-6.1 Sol86.0%
  3. #4Gemini 3.8 Flash85.6%
  4. #5Claude Opus 584.7%
artificialanalysis.ai · 2026-09-24
#9/8582.0%Verified
  1. #1Claude Opus 5.587.7%
  2. #8Gemini 3.1 Pro82.4%
  3. #9Muse Spark 1.382.0%
  4. #10Intern-S2-397B81.7%
artificialanalysis.ai · 2026-09-24
CharXiv Reasoning
day 0
~#3/9~84.6%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. ~#3Claude Haiku 5.5Estimated84.6%
  4. #3Qwen3.8 Flash-Next84.6%
estimated from related benchmarks
#1/886.2%Lab-reported
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
deepmind.google · 2026-09-02
~#4/9~84.0%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. #3Qwen3.8 Flash-Next84.6%
  3. ~#4Muse Spark 1.3Estimated84.0%
  4. #4Qwen3.8-Omni-Flash83.5%
estimated from related benchmarks
OmniDocBench v1.5
third-party
~#4/8~89.2%Estimated
  1. #1MiniMax-M391.6%
  2. #2Qwen3.8 27B91.1%
  3. ~#4Claude Haiku 5.5Estimated89.2%
  4. #4Gemini 3.1 Pro85.3%
estimated from related benchmarks
~#4/8~89.8%Estimated
  1. #1MiniMax-M391.6%
  2. #2Qwen3.8 27B91.1%
  3. ~#4Gemini 3.8 FlashEstimated89.8%
  4. #4Gemini 3.1 Pro85.3%
estimated from related benchmarks
~#4/8~90.5%Estimated
  1. #1MiniMax-M391.6%
  2. #2Qwen3.8 27B91.1%
  3. ~#4Muse Spark 1.3Estimated90.5%
  4. #4Gemini 3.1 Pro85.3%
estimated from related benchmarks
GDP.pdf (AA)
third-party
~#11/44~21.3%Estimated
  1. #1GPT-6.1 Sol32.0%
  2. #10Claude Opus 521.6%
  3. ~#11Claude Haiku 5.5Estimated21.3%
  4. #11GPT-5.521.2%
estimated from related benchmarks
#12/4321.0%Verified
  1. #1GPT-6.1 Sol32.0%
  2. #11GPT-5.521.2%
  3. #12Gemini 3.8 Flash21.0%
  4. #13GPT-6 Luna20.4%
artificialanalysis.ai · 2026-09-24
#3/4326.6%BestVerified
  1. #1GPT-6.1 Sol32.0%
  2. #2GPT-6 Astra31.0%
  3. #3Muse Spark 1.326.6%
  4. #4Claude Fable 5.126.2%
artificialanalysis.ai · 2026-09-24
Chartography
third-party
#4/2346.4%BestLab-reported
  1. #1GPT-6 Astra71.0%
  2. #3GPT-6 Sol53.6%
  3. #4Claude Haiku 5.546.4%
  4. #5Claude Fable 5.146.2%
anthropic.com · 2026-10-07
#6/2340.9%Verified
  1. #1GPT-6 Astra71.0%
  2. #5Claude Fable 5.146.2%
  3. #6Gemini 3.8 Flash40.9%
  4. #7GPT-5.6 Terra34.0%
surgehq.ai · 2026-09-24
#11/2327.6%Verified
  1. #1GPT-6 Astra71.0%
  2. #9Qwen3.8 Max (0902)29.1%
  3. #11Muse Spark 1.327.6%
  4. #12Claude Opus 527.3%
surgehq.ai · 2026-09-24

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 Haiku 5.5
Gemini 3.8 Flash
Muse Spark 1.3
GPQA Diamond
day 0
~#3/184~95.0%Estimated
  1. #1GPT-6 Astra96.1%
  2. #2Gemini 3.8 Flash95.3%
  3. ~#3Claude Haiku 5.5Estimated95.0%
  4. #3Gemini 3.1 Pro94.1%
estimated from related benchmarks
#2/18395.3%BestVerified
  1. #1GPT-6 Astra96.1%
  2. #2Gemini 3.8 Flash95.3%
  3. #3Gemini 3.1 Pro94.1%
artificialanalysis.ai · 2026-09-24
#5/18393.5%Verified
  1. #1GPT-6 Astra96.1%
  2. #5Kimi K393.5%
  3. #5Muse Spark 1.393.5%
  4. #5Qwen3.8 2.4T A95B93.5%
artificialanalysis.ai · 2026-09-24
Humanity's Last Exam
day 0
#16/18444.4%Verified
  1. #1Claude Opus 5.561.4%
  2. #15GPT-5.545.8%
  3. #16Claude Haiku 5.544.4%
  4. #17Grok 4.644.1%
artificialanalysis.ai · 2026-10-07
#11/18447.8%Verified
  1. #1Claude Opus 5.561.4%
  2. #10GPT-6 Sol47.9%
  3. #11Gemini 3.8 Flash47.8%
  4. #12Gemini 3.1 Pro47.0%
artificialanalysis.ai · 2026-09-24
#9/18448.7%BestVerified
  1. #1Claude Opus 5.561.4%
  2. #8MiMo-V2.6-Pro49.4%
  3. #9Muse Spark 1.348.7%
  4. #10GPT-6 Sol47.9%
artificialanalysis.ai · 2026-09-24
AIME (latest)
day 0
~#2/32~97.9%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Claude Haiku 5.5Estimated97.9%
  3. #2Inkling97.1%
estimated from related benchmarks
~#3/32~96.9%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. #2Inkling97.1%
  3. ~#3Gemini 3.8 FlashEstimated96.9%
  4. #3Ternary Bonsai 2 27B95.8%
estimated from related benchmarks
~#2/32~99.0%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Muse Spark 1.3Estimated99.0%
  3. #2Inkling97.1%
estimated from related benchmarks
AA Intelligence Index
third-party
#17/8543.4Verified
  1. #1Claude Opus 5.557.6
  2. #16Kimi K343.6
  3. #17Claude Haiku 5.543.4
  4. #18GPT-5.6 Terra42.1
artificialanalysis.ai · 2026-10-07
#20/8540.9Verified
  1. #1Claude Opus 5.557.6
  2. #19GLM-5.3 Flash41.8
  3. #20Gemini 3.8 Flash40.9
  4. #21Qwen3.8 2.4T A95B39.9
artificialanalysis.ai · 2026-09-24
#8/8548.1BestVerified
  1. #1Claude Opus 5.557.6
  2. #7Claude Opus 550.8
  3. #8Muse Spark 1.348.1
  4. #9GPT-6 Sol47.5
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
Claude Haiku 5.5
Gemini 3.8 Flash
Muse Spark 1.3
τ²-bench (Telecom)
day 0
—
~#2/118~98.3%Estimated
  1. #1Step 3.7 Flash98.5%
  2. ~#2Gemini 3.8 FlashEstimated98.3%
  3. #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
estimated from related benchmarks
~#2/118~98.3%Estimated
  1. #1Step 3.7 Flash98.5%
  2. ~#2Muse Spark 1.3Estimated98.3%
  3. #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
estimated from related benchmarks
OSWorld-Verified
day 0
—
~#4/12~82.1%Estimated
  1. #1Kimi K384.8%
  2. #3Nex-N2.5-Pro82.2%
  3. ~#4Gemini 3.8 FlashEstimated82.1%
  4. #4MiMo-V2.6-Pro82.0%
estimated from related benchmarks
~#3/12~84.2%Estimated
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. ~#3Muse Spark 1.3Estimated84.2%
  4. #3Nex-N2.5-Pro82.2%
estimated from related benchmarks
OSWorld 2.0
day 0
—
~#3/5~54.1%Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Gemini 3.8 FlashEstimated54.1%
  4. #3GPT-5.6 Terra50.2%
estimated from related benchmarks
~#3/5~57.8%Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Muse Spark 1.3Estimated57.8%
  4. #3GPT-5.6 Terra50.2%
estimated from related benchmarks
BrowseComp
day 0
—
~#7/18~88.1%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #6Step 5 Preview88.7%
  3. ~#7Gemini 3.8 FlashEstimated88.1%
  4. #7GPT-5.6 Terra87.5%
estimated from related benchmarks
~#3/18~91.3%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. ~#3Muse Spark 1.3Estimated91.3%
  4. #3Kimi K391.2%
estimated from related benchmarks
GDPval-AA (Elo)
third-party
—
#22/871412Verified
  1. #1Claude Opus 5.51866
  2. #21GPT-5.6 Terra1432
  3. #22Gemini 3.8 Flash1412
  4. #23Qwen3.8 27B1409
artificialanalysis.ai · 2026-09-24
#6/871684BestVerified
  1. #1Claude Opus 5.51866
  2. #5MiMo-V2.6-Pro1686
  3. #6Muse Spark 1.31684
  4. #7Qwen3.8 Max (0902)1668
artificialanalysis.ai · 2026-10-07
AutomationBench-AA
third-party
—
#10/8159.9%BestVerified
  1. #1Claude Opus 5.569.5%
  2. #9GLM-5.3 Flash60.4%
  3. #10Gemini 3.8 Flash59.9%
  4. #10Mistral Large 459.9%
artificialanalysis.ai · 2026-09-24
#16/8157.9%Verified
  1. #1Claude Opus 5.569.5%
  2. #15Kimi K358.3%
  3. #16Muse Spark 1.357.9%
  4. #17Qwen3.8 2.4T A95B57.2%
artificialanalysis.ai · 2026-09-24
τ-Bench Banking (AA)
third-party
—
#10/8944.9%Verified
  1. #1Muse Spark 1.350.5%
  2. #9Qwen3.8 Flash-Next45.4%
  3. #10Gemini 3.8 Flash44.9%
  4. #11Grok 4.643.3%
artificialanalysis.ai · 2026-09-24
#1/8950.5%BestVerified
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
artificialanalysis.ai · 2026-09-24
Not comparable across labs (1)
OSWorld 2.0 (release not stated)
day 0
—
—
#1/466.9%Lab-reported
  1. #1Muse Spark 1.366.9%
  2. #2Nex-N2.5-Pro56.4%
dev.meta.ai · 2026-09-02