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.
Laguna S 2.1MiniMax-M3Inkling Small
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
  • Laguna S 2.1
    Quality
    41.2
    Rank
    #52/119
    Price
    —
    Speed
    —

    vs MiniMax-M3: −0.5 quality · price n/a

  • MiniMax-M3
    Quality
    41.6
    Rank
    #51/119
    Price
    $0.52/M tok
    Speed
    88tok/s
    In$0.30▾Out$1.20▾/M tok

    vs Laguna S 2.1: +0.5 quality · price n/a

  • Inkling Small
    Quality
    40.0
    Rank
    #53/119
    Price
    $0.52/M tok
    Speed
    206tok/s
    In$0.30▾Out$1.20▾/M tok

    vs MiniMax-M3: −1.6 quality · 1× price

Overview

Metric
Laguna S 2.1
MiniMax-M3
Inkling Small
Lab
poolside
MiniMax
Thinking Machines Lab
Released
Jul 21, 2026
Jun 1, 2026
Jul 30, 2026
Weights
Open
Open
Open
Input price
$/M tok
—
$0.30Best
$0.30Best
Output price
$/M tok
—
$1.20Best
$1.20Best
Blended price
$/M tok · 3:1 in:out
—
$0.525Best
$0.525Best
Output speed
tok/s
—
88
⚡ SambaNova 246
206Best
Context
tokens
1MBest
1M
1M

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
Laguna S 2.1
MiniMax-M3
Inkling Small
Coding
41.2±9.8
#52/119Lab-reported
41.6±5.4Best
#51/119Mixed
40.0±8.0
#53/119Verified
Writing & chat
Not ranked
68.6±4.1
#31/156Verified
Not ranked
Vision
Not ranked
63.7±5.3Best
#30/91Mixed
58.2±8.2
#39/91Verified
Hard reasoning
Not ranked
70.1±3.7Best
#40/200Verified
64.5±3.7
#52/200Verified
Agents
Not ranked
47.3±3.4Best
#42/178Mixed
44.3±10.0
#53/178Verified

Coding benchmarks

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

Metric
Laguna S 2.1
MiniMax-M3
Inkling Small
SWE-bench Verified
day 0
~#3/14~81.1%Estimated
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. ~#3Laguna S 2.1Estimated81.1%
  4. #3Gemini 3.1 Pro80.6%
estimated from related benchmarks
#4/1380.5%Lab-reported
  1. #1Claude Opus 596.0%
  2. #3Gemini 3.1 Pro80.6%
  3. #4MiniMax-M380.5%
  4. #5Hy378.0%
minimax.io · 2026-06-01
~#6/14~77.8%Estimated
  1. #1Claude Opus 596.0%
  2. #5Hy378.0%
  3. ~#6Inkling SmallEstimated77.8%
  4. #6Inkling77.6%
estimated from related benchmarks
SWE-bench Pro (Public)
day 0
#11/1959.4%BestLab-reported
  1. #1Claude Opus 5.589.9%
  2. #10Atria Dawn Preview59.6%
  3. #11Laguna S 2.159.4%
  4. #12MiniMax-M359.0%
huggingface.co · 2026-07-21
#12/1959.0%Lab-reported
  1. #1Claude Opus 5.589.9%
  2. #11Laguna S 2.159.4%
  3. #12MiniMax-M359.0%
  4. #13GPT-5.558.6%
minimax.io · 2026-06-01
~#15/20~56.9%Estimated
  1. #1Claude Opus 5.589.9%
  2. #14Hy357.9%
  3. ~#15Inkling SmallEstimated56.9%
  4. #15Inkling54.3%
estimated from related benchmarks
DeepSWE v1.1
day 0
#32/3440.4%Lab-reported
  1. #1Gemini 4 Argon78.8%
  2. #31Qwen3.8 27B42.2%
  3. #32Laguna S 2.140.4%
  4. #33Nex-N2.5-Mini36.1%
huggingface.co · 2026-07-21
~#30/35~53.7%Estimated
  1. #1Gemini 4 Argon78.8%
  2. #29Nex-N2.5-Pro55.8%
  3. ~#30MiniMax-M3Estimated53.7%
  4. #30Qwen3.8 Max (0902)51.0%
estimated from related benchmarks
~#30/35~55.0%Estimated
  1. #1Gemini 4 Argon78.8%
  2. #29Nex-N2.5-Pro55.8%
  3. ~#30Inkling SmallEstimated55.0%
  4. #30Qwen3.8 Max (0902)51.0%
estimated from related benchmarks
Terminal-Bench 4.0
day 0
~#30/89~11.1%Estimated
  1. #1Claude Sonnet 5.563.6%
  2. #27Kimi K312.6%
  3. ~#30Laguna S 2.1Estimated11.1%
  4. #30Qwen3.8 2.4T A95B11.1%
estimated from related benchmarks
#33/882.0%BestVerified
  1. #1Claude Sonnet 5.563.6%
  2. #33GPT-5.4 mini2.0%
  3. #33MiniMax-M32.0%
  4. #35K2 Horizon 375B A23B1.5%
artificialanalysis.ai · 2026-09-24
#36/881.0%Verified
  1. #1Claude Sonnet 5.563.6%
  2. #36Inkling1.0%
  3. #36Inkling Small1.0%
  4. #36K2 Horizon 7B1.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBench
third-party
~#10/25~77.4%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #9gpt-oss-20b77.7%
  3. ~#10Laguna S 2.1Estimated77.4%
  4. #10Bonsai 27B76.4%
estimated from related benchmarks
~#12/25~71.4%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #11Maple-Preview75.1%
  3. ~#12MiniMax-M3Estimated71.4%
  4. #12Mistral Small 464.0%
estimated from related benchmarks
~#12/25~70.8%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #11Maple-Preview75.1%
  3. ~#12Inkling SmallEstimated70.8%
  4. #12Mistral Small 464.0%
estimated from related benchmarks
SciCode
third-party
~#37/106~49.4%Estimated
  1. #1Claude Opus 5.566.9%
  2. #36Inkling Small49.7%
  3. ~#37Laguna S 2.1Estimated49.4%
  4. #37Hy348.6%
estimated from related benchmarks
#44/10547.1%Verified
  1. #1Claude Opus 5.566.9%
  2. #43GPT-5.4 nano47.2%
  3. #44MiniMax-M347.1%
  4. #45Inkling47.0%
artificialanalysis.ai · 2026-09-24
#36/10549.7%BestVerified
  1. #1Claude Opus 5.566.9%
  2. #35Qwen3.8 Flash-Next50.6%
  3. #36Inkling Small49.7%
  4. #37Hy348.6%
artificialanalysis.ai · 2026-09-24
AA Coding Agent Index
third-party
~last/18below measured range (<41.1)Estimated
  1. #1Claude Opus 5.566.0
  2. #17GPT-6 Luna41.1
  3. ~#18Laguna S 2.1Estimated<41.1
estimated from related benchmarks
~#17/18~41.1Estimated
  1. #1Claude Opus 5.566.0
  2. #16Gemini 3.8 Flash41.9
  3. ~#17MiniMax-M3Estimated41.1
  4. #17GPT-6 Luna41.1
estimated from related benchmarks
~last/18below measured range (<41.1)Estimated
  1. #1Claude Opus 5.566.0
  2. #17GPT-6 Luna41.1
  3. ~#18Inkling SmallEstimated<41.1
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
Laguna S 2.1
MiniMax-M3
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
Laguna S 2.1
MiniMax-M3
Inkling Small
MMMU
day 0
—
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2MiniMax-M3Estimated71.3%
  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
—
#20/8578.6%BestVerified
  1. #1Claude Opus 5.587.7%
  2. #18Ling-3.0-flash-VL79.0%
  3. #20MiniMax-M378.6%
  4. #21GPT-5.3 Codex78.5%
artificialanalysis.ai · 2026-09-24
#39/8574.0%Verified
  1. #1Claude Opus 5.587.7%
  2. #38Muse Glimmer74.3%
  3. #39Inkling Small74.0%
  4. #40DeepSeek V4.1 Flash NVFP473.7%
artificialanalysis.ai · 2026-09-24
CharXiv Reasoning
day 0
—
~#5/9~79.3%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. #4Qwen3.8-Omni-Flash83.5%
  3. ~#5MiniMax-M3Estimated79.3%
  4. #5Muse Glimmer78.8%
estimated from related benchmarks
~#7/9~78.0%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. #6Inkling78.1%
  3. ~#7Inkling SmallEstimated78.0%
  4. #7Claude Sonnet 577.0%
estimated from related benchmarks
OmniDocBench v1.5
third-party
—
#1/791.6%Lab-reported
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
minimax.io · 2026-06-01
~#5/8~84.2%Estimated
  1. #1MiniMax-M391.6%
  2. #4Gemini 3.1 Pro85.3%
  3. ~#5Inkling SmallEstimated84.2%
  4. #5Claude Haiku 4.579.6%
estimated from related benchmarks
GDP.pdf (AA)
third-party
—
#30/439.8%Verified
  1. #1GPT-6.1 Sol32.0%
  2. #29Muse Glimmer10.0%
  3. #30MiniMax-M39.8%
  4. #31Ling-3.0-flash-VL8.4%
artificialanalysis.ai · 2026-09-24
~#25/44~12.9%Estimated
  1. #1GPT-6.1 Sol32.0%
  2. #24Claude Sonnet 513.2%
  3. ~#25Inkling SmallEstimated12.9%
  4. #25DeepSeek V4.1 Flash12.8%
estimated from related benchmarks
Chartography
third-party
—
~#16/24~20.0%Estimated
  1. #1GPT-6 Astra71.0%
  2. #15Grok 4.620.5%
  3. ~#16MiniMax-M3Estimated20.0%
  4. #16Muse Glimmer17.2%
estimated from related benchmarks
~#16/24~19.2%Estimated
  1. #1GPT-6 Astra71.0%
  2. #15Grok 4.620.5%
  3. ~#16Inkling SmallEstimated19.2%
  4. #16Muse Glimmer17.2%
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
Laguna S 2.1
MiniMax-M3
Inkling Small
GPQA Diamond
day 0
—
#12/18392.9%BestVerified
  1. #1GPT-6 Astra96.1%
  2. #11Claude Opus 593.2%
  3. #12MiniMax-M392.9%
  4. #13DeepSeek V4 Pro (0813)92.8%
artificialanalysis.ai · 2026-09-24
#33/18389.5%Verified
  1. #1GPT-6 Astra96.1%
  2. #33Grok Build 0.1 061689.5%
  3. #33Inkling Small89.5%
  4. #35Qwen3.5 397B A17B89.3%
artificialanalysis.ai · 2026-09-24
Humanity's Last Exam
day 0
—
#29/18439.0%BestVerified
  1. #1Claude Opus 5.561.4%
  2. #28DeepSeek V4.1 Flash39.2%
  3. #29MiniMax-M339.0%
  4. #30GPT-6 Luna38.5%
artificialanalysis.ai · 2026-09-24
#43/18433.3%Verified
  1. #1Claude Opus 5.561.4%
  2. #42Hy333.5%
  3. #43Inkling Small33.3%
  4. #44K2 Horizon 375B A23B32.0%
artificialanalysis.ai · 2026-09-24
AIME (latest)
day 0
—
~#5/32~94.5%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. #4Muse Glimmer94.7%
  3. ~#5MiniMax-M3Estimated94.5%
  4. #5Nova 2.0 Lite94.3%
estimated from related benchmarks
~#2/32~97.1%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Inkling SmallEstimated97.1%
  3. #2Inkling97.1%
estimated from related benchmarks
AA Intelligence Index
third-party
—
#31/8529.2BestVerified
  1. #1Claude Opus 5.557.6
  2. #30Gemini 3.1 Pro29.7
  3. #31MiniMax-M329.2
  4. #32Quasar 438B26.7
artificialanalysis.ai · 2026-09-24
#36/8525.7Verified
  1. #1Claude Opus 5.557.6
  2. #35Kimi K2.7 Code25.8
  3. #36Inkling Small25.7
  4. #37Hy325.3
artificialanalysis.ai · 2026-10-02

Agents benchmarks

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

Metric
Laguna S 2.1
MiniMax-M3
Inkling Small
τ²-bench (Telecom)
day 0
—
#18/11788.9%Verified
  1. #1Step 3.7 Flash98.5%
  2. #17KAT Coder Pro V289.5%
  3. #18MiniMax-M388.9%
  4. #19Qwen3.5 Omni Plus88.3%
artificialanalysis.ai · 2026-09-24
~#35/118~80.2%Estimated
  1. #1Step 3.7 Flash98.5%
  2. #34Nova 2.0 Omni80.4%
  3. ~#35Inkling SmallEstimated80.2%
  4. #35LongCat Flash Lite79.5%
estimated from related benchmarks
OSWorld-Verified
day 0
—
~#10/12~70.7%Estimated
  1. #1Kimi K384.8%
  2. #9Nex-N2.5-Mini71.2%
  3. ~#10MiniMax-M3Estimated70.7%
  4. #10Muse Glimmer65.9%
estimated from related benchmarks
~#10/12~69.6%Estimated
  1. #1Kimi K384.8%
  2. #9Nex-N2.5-Mini71.2%
  3. ~#10Inkling SmallEstimated69.6%
  4. #10Muse Glimmer65.9%
estimated from related benchmarks
OSWorld 2.0
day 0
—
~last/5below measured range (<47.5%)Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #4GPT-5.547.5%
  3. ~#5MiniMax-M3Estimated<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
—
#12/1783.5%Lab-reported
  1. #1Atria Dawn Preview92.5%
  2. #11Hy384.2%
  3. #12MiniMax-M383.5%
  4. #13Nex-N2.5-Mini83.4%
minimax.io · 2026-06-01
~#15/18~67.0%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #14Inkling77.1%
  3. ~#15Inkling SmallEstimated67.0%
  4. #15Mistral Medium 3.548.6%
estimated from related benchmarks
GDPval-AA (Elo)
third-party
—
#27/871230Verified
  1. #1Claude Opus 5.51866
  2. #26GPT-5.51336
  3. #27MiniMax-M31230
  4. #28Apodex 1.11189
artificialanalysis.ai · 2026-09-24
~#25/88~1360Estimated
  1. #1Claude Opus 5.51866
  2. #24GPT-6 Luna1367
  3. ~#25Inkling SmallEstimated1360
  4. #25K2 Horizon 375B A23B1349
estimated from related benchmarks
AutomationBench-AA
third-party
—
#36/8121.3%Verified
  1. #1Claude Opus 5.569.5%
  2. #35Quasar 438B23.9%
  3. #36MiniMax-M321.3%
  4. #37K2 Horizon 7B20.9%
artificialanalysis.ai · 2026-09-24
~#36/82~23.9%Estimated
  1. #1Claude Opus 5.569.5%
  2. #35Quasar 438B23.9%
  3. ~#36Inkling SmallEstimated23.9%
  4. #36MiniMax-M321.3%
estimated from related benchmarks
τ-Bench Banking (AA)
third-party
—
#46/8915.3%Verified
  1. #1Muse Spark 1.350.5%
  2. #45A.X-K216.1%
  3. #46MiniMax-M315.3%
  4. #46Qwen3.5 122B A10B15.3%
artificialanalysis.ai · 2026-09-24
#40/8918.8%BestVerified
  1. #1Muse Spark 1.350.5%
  2. #39K2 Horizon 3.7B19.6%
  3. #40Inkling Small18.8%
  4. #41Ring-2.6-1T17.9%
artificialanalysis.ai · 2026-09-24
Not comparable across labs (1)
OSWorld-Verified (task subset)
day 0
—
#1/170.1%Lab-reported
minimax.io · 2026-06-01
—