Skip to content
Model Pareto

Gemini 4 Argon vs Muse Wonder

Gemini 4 Argon scores higher than Muse Wonder in both shared categories. Muse Wonder costs 2× as much as Gemini 4 Argon ($8.00 vs $4.00 per million tokens, blended 3:1 input:output).
Gemini 4 ArgonMuse Wonder
Focus

Coding: quality vs price

Compared models are ringed; the other 131 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, Kimi K3.1 Pro, Claude Opus 5.5. 43 models are not plotted: Muse Wonder Full, GLM-5.3 Flash NVFP4, DeepSeek V4.1 Flash NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, GLM-5.3 NVFP4, Atria Dawn Preview, Ternary Bonsai 27B, Xing4.0-29B-A4B, Beam 1.0 501B A23B, Qwen3.8 27B NVFP4, Maple-Preview, Intern-S2-397B, Bonsai 27B, Solar Open2 250B, Muse Spark Open, Laguna S 2.1, Phi-4-reasoning-plus, Motif 3, Nex-N2-Pro, Flint, Nemotron 3.5 Super VL NVFP4, Nemotron 3.5 Super VL, K2 Horizon 375B A23B, K-EXAONE 2.0 0803, A.X-K2, Intern-S2-Preview (35B-A3B), Nemotron 3.5 Bolt 74B-A9B, K2 Horizon MoVA 36B A4B, G9v3-39A5B, North Mini Code, Qwen3.8 Flash-Next NVFP4, LFM2.5-24B-A2B, K2 Horizon 7B, K2-Horizon-32B, Devstral 2, NVIDIA Nemotron-Labs Dory1.0 4B, MiniCPM5-2B, Falcon-H1-34B-Instruct, Devstral Small 2, Ling 3.0 Tiny, K2 Horizon 3.7B, K2 Horizon 0.9B, LFM2.5-2.6B.

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

Muse Wonder Full, GLM-5.3 Flash NVFP4, DeepSeek V4.1 Flash NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, GLM-5.3 NVFP4, Atria Dawn Preview, Ternary Bonsai 27B, Xing4.0-29B-A4B, Beam 1.0 501B A23B, Qwen3.8 27B NVFP4, Maple-Preview, Intern-S2-397B, Bonsai 27B, Solar Open2 250B, Muse Spark Open, Laguna S 2.1, Phi-4-reasoning-plus, Motif 3, Nex-N2-Pro, Flint, Nemotron 3.5 Super VL NVFP4, Nemotron 3.5 Super VL, K2 Horizon 375B A23B, K-EXAONE 2.0 0803, A.X-K2, Intern-S2-Preview (35B-A3B), Nemotron 3.5 Bolt 74B-A9B, K2 Horizon MoVA 36B A4B, G9v3-39A5B, North Mini Code, Qwen3.8 Flash-Next NVFP4, LFM2.5-24B-A2B, K2 Horizon 7B, K2-Horizon-32B, Devstral 2, NVIDIA Nemotron-Labs Dory1.0 4B, MiniCPM5-2B, Falcon-H1-34B-Instruct, Devstral Small 2, 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
  • Gemini 4 Argon
    Quality
    88.7
    Rank
    #5/133
    Price
    $4.00/M tok
    Speed
    —
    In$2.00▾Out$10▾/M tok

    vs Muse Wonder: +4.0 quality · 0.5× price

  • Muse Wonder
    Quality
    84.7
    Rank
    #8/133
    Price
    $8.00/M tok
    Speed
    101tok/s
    In$4.00Out$20/M tok

    vs Gemini 4 Argon: −4.0 quality · 2× price

Overview

Metric
Gemini 4 Argon
Muse Wonder
Lab
Google DeepMind
Meta
Released
Sep 30, 2026
Oct 12, 2026
Weights
Proprietary
Proprietary
Input price
$/M tok
$2.00Best
$4.00
Output price
$/M tok
$10Best
$20
Blended price
$/M tok · 3:1 in:out
$4.00Best
$8.00
Output speed
tok/s
—
101
Context
tokens
1M
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
Gemini 4 Argon
Muse Wonder
Coding
88.7±4.5Best
#5/133Verified
84.7±4.5
#8/133Verified
Writing & chat
94.5±6.0
#1/160Verifiedbest value
Not ranked
Vision
Not ranked
91.4±9.0
#4/97Verified
Hard reasoning
94.5±5.1Best
#4/213Verified
90.3±5.1
#10/213Verified
Agents
Not ranked
92.8±7.5
#3/186Verified

Coding benchmarks

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

Metric
Gemini 4 Argon
Muse Wonder
SWE-bench Verified
day 0
~#2/20~93.7%Estimated
  1. #1Claude Opus 596.0%
  2. ~#2Gemini 4 ArgonEstimated93.7%
  3. #2Claude Sonnet 585.2%
estimated from related benchmarks
~#2/20~92.2%Estimated
  1. #1Claude Opus 596.0%
  2. ~#2Muse WonderEstimated92.2%
  3. #2Claude Sonnet 585.2%
estimated from related benchmarks
SWE-bench Pro (Public)
day 0
~#5/23~78.5%Estimated
  1. #1Claude Opus 5.589.9%
  2. #4Claude Opus 579.2%
  3. ~#5Gemini 4 ArgonEstimated78.5%
  4. #5Intern-S2-397B68.5%
estimated from related benchmarks
~#5/23~76.0%Estimated
  1. #1Claude Opus 5.589.9%
  2. #4Claude Opus 579.2%
  3. ~#5Muse WonderEstimated76.0%
  4. #5Intern-S2-397B68.5%
estimated from related benchmarks
DeepSWE v1.1
day 0
#1/4278.8%BestVerified
  1. #1Gemini 4 Argon78.8%
  2. #2DeepSeek V4.1 Flash 101777.0%
artificialanalysis.ai · 2026-10-07
#4/4275.8%Verified
  1. #1Gemini 4 Argon78.8%
  2. #2Muse Wonder Full77.0%
  3. #4Muse Wonder75.8%
  4. #5DeepSeek V4.1 Flash74.2%
artificialanalysis.ai · 2026-10-15
Terminal-Bench 4.0
day 0
#5/9857.1%BestVerified
  1. #1Kimi K3.1 Pro67.2%
  2. #4GPT-6 Astra59.1%
  3. #5Gemini 4 Argon57.1%
  4. #5Muse Wonder Full57.1%
artificialanalysis.ai · 2026-10-02
#8/9852.0%Verified
  1. #1Kimi K3.1 Pro67.2%
  2. #8Claude Fable 5.152.0%
  3. #8Muse Wonder52.0%
  4. #10Claude Opus 549.0%
artificialanalysis.ai · 2026-10-13
LiveCodeBench
third-party
~#2/28~92.3%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. ~#2Gemini 4 ArgonEstimated92.3%
  3. #2Qwen3.8 Flash-Next91.9%
estimated from related benchmarks
~#3/28~91.2%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. ~#3Muse WonderEstimated91.2%
  4. #3Qwen3.8 27B90.3%
estimated from related benchmarks
SciCode
third-party
#4/11761.8%BestVerified
  1. #1Claude Opus 5.566.9%
  2. #3Muse Wonder Full62.6%
  3. #4Gemini 4 Argon61.8%
  4. #5Claude Sonnet 5.561.0%
artificialanalysis.ai · 2026-10-02
#8/11760.3%Verified
  1. #1Claude Opus 5.566.9%
  2. #7Kimi K3.1 Pro60.8%
  3. #8Muse Wonder60.3%
  4. #9Kimi K359.5%
artificialanalysis.ai · 2026-10-13
AA Coding Agent Index
third-party
#8/2353.2BestVerified
  1. #1Claude Opus 5.561.7
  2. #7GPT-6.1 Sol54.1
  3. #8Gemini 4 Argon53.2
  4. #9Muse Wonder52.0
artificialanalysis.ai · 2026-10-24
#9/2352.0Verified
  1. #1Claude Opus 5.561.7
  2. #8Gemini 4 Argon53.2
  3. #9Muse Wonder52.0
  4. #10Mistral Large 449.8
artificialanalysis.ai · 2026-10-24
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
Gemini 4 Argon
Muse Wonder

Vision benchmarks

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

Metric
Gemini 4 Argon
Muse Wonder
MMMU
day 0
—
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2Muse WonderEstimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
MMMU-Pro
day 0
—
~#2/88~86.9%Estimated
  1. #1Claude Opus 5.587.7%
  2. ~#2Muse WonderEstimated86.9%
  3. #2GPT-6 Astra86.9%
estimated from related benchmarks
CharXiv Reasoning
day 0
—
~#2/12~85.8%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. ~#2Muse WonderEstimated85.8%
  3. #2Kimi K384.8%
estimated from related benchmarks
OmniDocBench v1.5
third-party
—
~#2/8~91.1%Estimated
  1. #1MiniMax-M391.6%
  2. ~#2Muse WonderEstimated91.1%
  3. #2Kimi K391.1%
estimated from related benchmarks
GDP.pdf (AA)
third-party
—
#4/4630.6%Verified
  1. #1Muse Wonder Full32.6%
  2. #2GPT-6.1 Sol31.0%
  3. #4Muse Wonder30.6%
  4. #5Muse Spark 1.326.6%
artificialanalysis.ai · 2026-10-13
Chartography
third-party
—
~#4/24~49.0%Estimated
  1. #1GPT-6 Astra71.0%
  2. #3GPT-6 Sol53.6%
  3. ~#4Muse WonderEstimated49.0%
  4. #4Claude Haiku 5.546.4%
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
Gemini 4 Argon
Muse Wonder
GPQA Diamond
day 0
~#2/191~96.1%Estimated
  1. #1GPT-6 Astra96.1%
  2. ~#2Gemini 4 ArgonEstimated96.1%
  3. #2Gemini 3.8 Flash95.3%
estimated from related benchmarks
~#2/191~96.1%Estimated
  1. #1GPT-6 Astra96.1%
  2. ~#2Muse WonderEstimated96.1%
  3. #2Gemini 3.8 Flash95.3%
estimated from related benchmarks
Humanity's Last Exam
day 0
#3/19757.1%BestVerified
  1. #1Claude Opus 5.561.4%
  2. #2Claude Fable 5.159.1%
  3. #3Gemini 4 Argon57.1%
  4. #4Claude Sonnet 5.555.0%
artificialanalysis.ai · 2026-10-02
#10/19750.1%Verified
  1. #1Claude Opus 5.561.4%
  2. #9Kimi K3.1 Pro52.5%
  3. #10Muse Wonder50.1%
  4. #11MiMo-V2.6-Pro49.4%
artificialanalysis.ai · 2026-10-13
AIME (latest)
day 0
~#2/33~99.1%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Gemini 4 ArgonEstimated99.1%
  3. #2Beam 1.0 501B A23B97.7%
estimated from related benchmarks
~#2/33~99.1%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Muse WonderEstimated99.1%
  3. #2Beam 1.0 501B A23B97.7%
estimated from related benchmarks
AA Intelligence Index
third-party
#7/10052.6BestVerified
  1. #1Claude Opus 5.557.6
  2. #6GPT-6 Astra52.7
  3. #7Gemini 4 Argon52.6
  4. #8Muse Wonder52.4
artificialanalysis.ai · 2026-10-02
#8/10052.4Verified
  1. #1Claude Opus 5.557.6
  2. #7Gemini 4 Argon52.6
  3. #8Muse Wonder52.4
  4. #9GPT-6.1 Sol51.8
artificialanalysis.ai · 2026-10-13

Agents benchmarks

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

Metric
Gemini 4 Argon
Muse Wonder
τ²-bench (Telecom)
day 0
—
~#3/120~98.2%Estimated
  1. #1Step 3.7 Flash98.5%
  2. #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
  3. ~#3Muse WonderEstimated98.2%
  4. #3Gemini 3.1 Pro95.6%
estimated from related benchmarks
OSWorld-Verified
day 0
—
~#2/15~84.3%Estimated
  1. #1Kimi K384.8%
  2. ~#2Muse WonderEstimated84.3%
  3. #2Qwen3.8 27B84.3%
estimated from related benchmarks
OSWorld 2.0
day 0
—
~#2/5~58.4%Estimated
  1. #1GLM-5.3 Flash59.1%
  2. ~#2Muse WonderEstimated58.4%
  3. #2Kimi K358.3%
estimated from related benchmarks
BrowseComp
day 0
—
~#2/22~92.0%Estimated
  1. #1Atria Dawn Preview92.5%
  2. ~#2Muse WonderEstimated92.0%
  3. #2GPT-6 Astra91.5%
estimated from related benchmarks
GDPval-AA (Elo)
third-party
—
#3/901770Verified
  1. #1Claude Opus 5.51866
  2. #2Muse Wonder Full1857
  3. #3Muse Wonder1770
  4. #4Claude Fable 5.11754
artificialanalysis.ai · 2026-10-13
AutomationBench-AA
third-party
—
#5/8368.1%Verified
  1. #1Muse Wonder Full71.3%
  2. #4GPT-6 Astra68.5%
  3. #5Muse Wonder68.1%
  4. #6Grok 4.667.0%
artificialanalysis.ai · 2026-10-13
τ-Bench Banking (AA)
third-party
—
~#4/91~48.8%Estimated
  1. #1Muse Spark 1.350.5%
  2. #3Qwen3.8 2.4T A95B49.1%
  3. ~#4Muse WonderEstimated48.8%
  4. #4Qwen3.8 27B48.0%
estimated from related benchmarks