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.
Command AOlmo 3.1 32B InstructRing-flash-2.0
Focus

Hard reasoning: quality vs price

Compared models are ringed; the other 179 ranked here are greyed.

Lower price is better. Pareto frontier: Gemma 4 E4B, Sarvam 30B, Qwen3.5 4B, Sarvam 105B, Ling 3.0 Flash, MiMo-V2.5, GPT-6 Luna, Qwen3.8 Flash-Next, GLM-5.3 Flash, MiMo-V2.6-Pro, Muse Spark 1.3, Claude Sonnet 5.5, Claude Opus 5.5. 70 models are not plotted: Motif 3, Nex-N2-Pro, K2 Horizon 375B A23B, A.X-K2, Solar Open2 250B, Xing4.0-29B-A4B, K2 Horizon MoVA 36B A4B, Intern-S2-Preview (35B-A3B), K-EXAONE 2.0 0803, G9v3-39A5B, K2 Horizon 7B, Phi-4-reasoning-plus, EXAONE 4.5 33B, Nanbeige4.1-3B, HyperNova 60B 2605, Nemotron Cascade 2 30B A3B, INTELLECT-3, Apriel-v1.6-15B-Thinker, Command A+, K2 Horizon 3.7B, Ling 3.0 Tiny, K2 Think V2, Step3 VL 10B, DiffusionGemma 26B A4B, K2-V2, North Mini Code, Falcon-H1R-7B, Solar Open 100B, Llama 3.1 Nemotron Ultra 253B v1, MiniCPM5-2B, LongCat Flash Lite, HyperCLOVA X SEED Think (32B), Tri-21B-Think, EXAONE 4.0 32B, Olmo 3.1 32B Think, LFM2.5-2.6B, Devstral 2, LFM2.5-8B-A1B, Olmo 3.1 32B Instruct, Olmo 3 7B Think, NVIDIA Nemotron 3 Nano 4B, Devstral Small 2, Phi-4-mini-flash-reasoning, Falcon-H1-34B-Instruct, Qwen3.5 2B, Hermes 4 - Llama-3.1 70B, LFM2 24B A2B, Exaone 4.0 1.2B, Llama 3.2 Instruct 90B (Vision), Gemma 4 E2B, Molmo2-8B, LFM2.5-1.2B-Thinking, LFM2.5-1.2B-Instruct, MiniCPM5-1B, Jamba 1.7 Large, MiniCPM-V 4.6 1.3B, Kimi Linear 48B A3B Instruct, Granite 4.0 Micro, Jamba Reasoning 3B, Jamba 1.7 Mini, Phi-4 Multimodal Instruct, Tiny Aya Global, LFM2.5-VL-1.6B, Granite 4.0 H 350M, K2 Horizon 0.9B, Qwen3.5 0.8B, Granite 4.0 350M, Granite 4.0 H 1B, Molmo 7B-D, Gemma 3 270M.

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

Motif 3, Nex-N2-Pro, K2 Horizon 375B A23B, A.X-K2, Solar Open2 250B, Xing4.0-29B-A4B, K2 Horizon MoVA 36B A4B, Intern-S2-Preview (35B-A3B), K-EXAONE 2.0 0803, G9v3-39A5B, K2 Horizon 7B, Phi-4-reasoning-plus, EXAONE 4.5 33B, Nanbeige4.1-3B, HyperNova 60B 2605, Nemotron Cascade 2 30B A3B, INTELLECT-3, Apriel-v1.6-15B-Thinker, Command A+, K2 Horizon 3.7B, Ling 3.0 Tiny, K2 Think V2, Step3 VL 10B, DiffusionGemma 26B A4B, K2-V2, North Mini Code, Falcon-H1R-7B, Solar Open 100B, Llama 3.1 Nemotron Ultra 253B v1, MiniCPM5-2B, LongCat Flash Lite, HyperCLOVA X SEED Think (32B), Tri-21B-Think, EXAONE 4.0 32B, Olmo 3.1 32B Think, LFM2.5-2.6B, Devstral 2, LFM2.5-8B-A1B, Olmo 3.1 32B Instruct, Olmo 3 7B Think, NVIDIA Nemotron 3 Nano 4B, Devstral Small 2, Phi-4-mini-flash-reasoning, Falcon-H1-34B-Instruct, Qwen3.5 2B, Hermes 4 - Llama-3.1 70B, LFM2 24B A2B, Exaone 4.0 1.2B, Llama 3.2 Instruct 90B (Vision), Gemma 4 E2B, Molmo2-8B, LFM2.5-1.2B-Thinking, LFM2.5-1.2B-Instruct, MiniCPM5-1B, Jamba 1.7 Large, MiniCPM-V 4.6 1.3B, Kimi Linear 48B A3B Instruct, Granite 4.0 Micro, Jamba Reasoning 3B, Jamba 1.7 Mini, Phi-4 Multimodal Instruct, Tiny Aya Global, LFM2.5-VL-1.6B, Granite 4.0 H 350M, K2 Horizon 0.9B, Qwen3.5 0.8B, Granite 4.0 350M, Granite 4.0 H 1B, Molmo 7B-D, Gemma 3 270M

  • Best-value frontier (nothing is both cheaper and better)
  • Evidencestrong → weak
  • Estimated from other categories
  • Command A
    Quality
    18.6
    Rank
    #143/182
    Price
    $4.38/M tok
    Speed
    57tok/s
    In$2.50Out$10/M tok

    vs Ring-flash-2.0: −16.8 quality · 18× price

  • Olmo 3.1 32B Instruct
    Quality
    20.2
    Rank
    #137/182
    Price
    —
    Speed
    —

    vs Ring-flash-2.0: −15.1 quality · price n/a

  • Ring-flash-2.0
    Quality
    35.3
    Rank
    #104/182
    Price
    $0.25/M tok
    Speed
    —
    In$0.14▾Out$0.57▾/M tok

    vs Olmo 3.1 32B Instruct: +15.1 quality · price n/a

Overview

Metric
Command A
Olmo 3.1 32B Instruct
Ring-flash-2.0
Lab
Cohere
Ai2 (Allen Institute)
inclusionAI (Ant Group)
Released
Mar 13, 2025
Jan 13, 2026
Sep 19, 2025
Weights
Open
Open
Open
Input price
$/M tok
$2.50
—
$0.14Best
Output price
$/M tok
$10
—
$0.57Best
Blended price
$/M tok · 3:1 in:out
$4.375
—
$0.247Best
Output speed
tok/s
57
—
—
Context
tokens
256KBest
66K
128K

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
Command A
Olmo 3.1 32B Instruct
Ring-flash-2.0
Writing & chat
23.6±9.5
#111/146Verified
23.4±4.2
#112/146Verified
23.9±4.5Best
#110/146Verified
Hard reasoning
18.6±5.8
#143/182Verified
20.2±5.8
#137/182Verified
35.3±5.8Best
#104/182Verified
Agents
17.3±10.0
#138/173Verified
18.8±10.0Best
#128/173Verified
17.1±10.0
#139/173Verified

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
Command A
Olmo 3.1 32B Instruct
Ring-flash-2.0
GPQA Diamond
day 0
#131/17252.7%Verified
  1. #1GPT-6 Astra96.1%
  2. #130Reka Flash 352.9%
  3. #131Command A52.7%
  4. #132Olmo 3 7B Think51.6%
artificialanalysis.ai · 2026-09-24
#128/17253.9%Verified
  1. #1GPT-6 Astra96.1%
  2. #127Gemma 4 E4B54.9%
  3. #128Olmo 3.1 32B Instruct53.9%
  4. #129Devstral Small 253.2%
artificialanalysis.ai · 2026-09-24
#91/17272.5%BestVerified
  1. #1GPT-6 Astra96.1%
  2. #90Hermes 4 - Llama-3.1 405B72.7%
  3. #91Ring-flash-2.072.5%
  4. #92K2 Think V271.3%
artificialanalysis.ai · 2026-09-24
Humanity's Last Exam
day 0
#165/1784.0%Verified
  1. #1Claude Opus 5.561.4%
  2. #163Mistral Large 34.2%
  3. #165Command A4.0%
  4. #166Granite 4.0 H Small3.8%
artificialanalysis.ai · 2026-09-24
#142/1785.0%Verified
  1. #1Claude Opus 5.561.4%
  2. #142Granite 4.0 Micro5.0%
  3. #142Olmo 3.1 32B Instruct5.0%
  4. #142Phi-4 Multimodal Instruct5.0%
artificialanalysis.ai · 2026-09-24
#104/1789.6%BestVerified
  1. #1Claude Opus 5.561.4%
  2. #103Granite 4.2 8B9.7%
  3. #104Ring-flash-2.09.6%
  4. #105Nova 2.0 Pro Preview9.4%
artificialanalysis.ai · 2026-09-24
AIME (latest)
day 0
~#15/25~36.9%Estimated
  1. #1Inkling97.1%
  2. #14Mistral Large 338.0%
  3. ~#15Command AEstimated36.9%
  4. #15Devstral 236.7%
estimated from related benchmarks
~#14/25~39.0%Estimated
  1. #1Inkling97.1%
  2. #13Phi-4-reasoning-plus78.0%
  3. ~#14Olmo 3.1 32B InstructEstimated39.0%
  4. #14Mistral Large 338.0%
estimated from related benchmarks
~#14/25~62.8%Estimated
  1. #1Inkling97.1%
  2. #13Phi-4-reasoning-plus78.0%
  3. ~#14Ring-flash-2.0Estimated62.8%
  4. #14Mistral Large 338.0%
estimated from related benchmarks
AA Intelligence Index
third-party
~#73/75~4.8Estimated
  1. #1Claude Opus 5.557.6
  2. #72Ministral 3 8B5.5
  3. ~#73Command AEstimated4.8
  4. #73Ministral 3 3B4.8
estimated from related benchmarks
~#72/75~5.6Estimated
  1. #1Claude Opus 5.557.6
  2. #71Ministral 3 14B6.0
  3. ~#72Olmo 3.1 32B InstructEstimated5.6
  4. #72Ministral 3 8B5.5
estimated from related benchmarks
~#58/75~11.6Estimated
  1. #1Claude Opus 5.557.6
  2. #57Mercury 2.512.3
  3. ~#58Ring-flash-2.0Estimated11.6
  4. #58gpt-oss-120b11.6
estimated from related benchmarks
Benchmarks in other categories (2)

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
Command A
Olmo 3.1 32B Instruct
Ring-flash-2.0
IFBench
day 0
#82/12536.5%Verified
  1. #1MiniMax-M382.9%
  2. #81HyperCLOVA X SEED Think (32B)37.9%
  3. #82Command A36.5%
  4. #83Mistral Large 336.2%
artificialanalysis.ai · 2026-09-24
#77/12539.2%Verified
  1. #1MiniMax-M382.9%
  2. #76Llama 4 Scout39.5%
  3. #77Olmo 3.1 32B Instruct39.2%
  4. #78ERNIE 4.5 300B A47B39.1%
artificialanalysis.ai · 2026-09-24
#69/12543.3%BestVerified
  1. #1MiniMax-M382.9%
  2. #68LFM2.5-1.2B-Instruct43.8%
  3. #69Ring-flash-2.043.3%
  4. #70LongCat Flash Lite43.1%
artificialanalysis.ai · 2026-09-24
MMMLU
day 0
~last/5below measured range (<81.3%)Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. #4gpt-oss-120b81.3%
  3. ~#5Command AEstimated<81.3%
estimated from related benchmarks
~last/5below measured range (<81.3%)Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. #4gpt-oss-120b81.3%
  3. ~#5Olmo 3.1 32B InstructEstimated<81.3%
estimated from related benchmarks
~last/5below measured range (<81.3%)Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. #4gpt-oss-120b81.3%
  3. ~#5Ring-flash-2.0Estimated<81.3%
estimated from related benchmarks
LMArena Text, Non-English (Elo)
third-party
~#46/54~1308Estimated
  1. #1Claude Opus 5.51501
  2. #45Llama 4 Maverick1311
  3. ~#46Command AEstimated1308
  4. #46Llama 3.1 Nemotron Ultra 253B v1Few votes1306
estimated from related benchmarks
#49/531294BestVerified
  1. #1Claude Opus 5.51501
  2. #48gpt-oss-20b1299
  3. #49Olmo 3.1 32B Instruct1294
  4. #50Ring-flash-2.0Few votes1293
lmarena.ai · 2026-09-13
#50/531293VerifiedFew votes
  1. #1Claude Opus 5.51501
  2. #49Olmo 3.1 32B Instruct1294
  3. #50Ring-flash-2.0Few votes1293
  4. #51NVIDIA Nemotron 3 Nano 30B A3B1286
lmarena.ai · 2026-09-13
LMArena Text (Elo)
third-party
~#46/54~1333Estimated
  1. #1Claude Opus 5.51509
  2. #45Llama 3.1 Nemotron Ultra 253B v1Few votes1348
  3. ~#46Command AEstimated1333
  4. #46Olmo 3.1 32B Instruct1330
estimated from related benchmarks
#46/531330BestVerified
  1. #1Claude Opus 5.51509
  2. #45Llama 3.1 Nemotron Ultra 253B v1Few votes1348
  3. #46Olmo 3.1 32B Instruct1330
  4. #47Llama 4 Maverick1327
lmarena.ai · 2026-09-13
#49/531321Verified
  1. #1Claude Opus 5.51509
  2. #48Molmo2-8BFew votes1322
  3. #49Ring-flash-2.01321
  4. #50gpt-oss-20b1317
lmarena.ai · 2026-09-13
EQ-Bench Creative Writing v3 (Elo)
third-party
~#22/26~1442Estimated
  1. #1GPT-6 Astra2173
  2. #21Gemini 3.1 Pro1491
  3. ~#22Command AEstimated1442
  4. #22Mistral Large 31412
estimated from related benchmarks
~#24/26~1254Estimated
  1. #1GPT-6 Astra2173
  2. #23Gemma 4 31B1368
  3. ~#24Olmo 3.1 32B InstructEstimated1254
  4. #24gpt-oss-120b961
estimated from related benchmarks
~#24/26~1280Estimated
  1. #1GPT-6 Astra2173
  2. #23Gemma 4 31B1368
  3. ~#24Ring-flash-2.0Estimated1280
  4. #24gpt-oss-120b961
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
Command A
Olmo 3.1 32B Instruct
Ring-flash-2.0
τ²-bench (Telecom)
day 0
#89/11515.2%Verified
  1. #1Step 3.7 Flash98.5%
  2. #88Llama 4 Scout15.5%
  3. #89Command A15.2%
  4. #90Granite 4.0 H 350M14.6%
artificialanalysis.ai · 2026-09-24
#77/11521.3%BestVerified
  1. #1Step 3.7 Flash98.5%
  2. #77NVIDIA Nemotron Nano 12B v2 VL21.3%
  3. #77Olmo 3.1 32B Instruct21.3%
  4. #79Exaone 4.0 1.2B20.5%
artificialanalysis.ai · 2026-09-24
#106/1150.0%Verified
  1. #1Step 3.7 Flash98.5%
  2. #106Reka Flash 30.0%
  3. #106Ring-flash-2.00.0%
  4. #106Tiny Aya Global0.0%
artificialanalysis.ai · 2026-09-24
OSWorld-Verified
day 0
~#11/12~62.9%Estimated
  1. #1Kimi K384.8%
  2. #10Muse Glimmer65.9%
  3. ~#11Command AEstimated62.9%
  4. #11Claude Haiku 4.550.7%
estimated from related benchmarks
~#11/12~62.4%Estimated
  1. #1Kimi K384.8%
  2. #10Muse Glimmer65.9%
  3. ~#11Olmo 3.1 32B InstructEstimated62.4%
  4. #11Claude Haiku 4.550.7%
estimated from related benchmarks
~#11/12~65.8%Estimated
  1. #1Kimi K384.8%
  2. #10Muse Glimmer65.9%
  3. ~#11Ring-flash-2.0Estimated65.8%
  4. #11Claude Haiku 4.550.7%
estimated from related benchmarks
OSWorld 2.0
day 0
~#3/5~53.8%Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Command AEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
estimated from related benchmarks
~#3/5~53.8%Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Olmo 3.1 32B InstructEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
estimated from related benchmarks
~#3/5~53.8%Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Ring-flash-2.0Estimated53.8%
  4. #3GPT-5.6 Terra50.2%
estimated from related benchmarks
BrowseComp
day 0
~#17/18~31.6%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #16Nemotron 3 Ultra44.4%
  3. ~#17Command AEstimated31.6%
  4. #17Mistral Small 421.3%
estimated from related benchmarks
~#17/18~33.5%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #16Nemotron 3 Ultra44.4%
  3. ~#17Olmo 3.1 32B InstructEstimated33.5%
  4. #17Mistral Small 421.3%
estimated from related benchmarks
~#17/18~36.0%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #16Nemotron 3 Ultra44.4%
  3. ~#17Ring-flash-2.0Estimated36.0%
  4. #17Mistral Small 421.3%
estimated from related benchmarks
GDPval-AA (Elo)
third-party
~#55/87~701Estimated
  1. #1Claude Opus 5.51846
  2. #54Claude Haiku 4.5719
  3. ~#55Command AEstimated701
  4. #55MiniCPM5-2B694
estimated from related benchmarks
~#56/87~694Estimated
  1. #1Claude Opus 5.51846
  2. #55MiniCPM5-2B694
  3. ~#56Olmo 3.1 32B InstructEstimated694
  4. #56Nemotron 3.5 Lightning624
estimated from related benchmarks
~#59/87~581Estimated
  1. #1Claude Opus 5.51846
  2. #58gpt-oss-120b596
  3. ~#59Ring-flash-2.0Estimated581
  4. #59Granite 4.2 30B564
estimated from related benchmarks
AutomationBench-AA
third-party
~#74/80~0.3%Estimated
  1. #1Claude Opus 5.569.5%
  2. #72Granite 4.2 3B0.4%
  3. ~#74Command AEstimated0.3%
  4. #74gpt-oss-120b0.2%
estimated from related benchmarks
~#74/80~0.2%Estimated
  1. #1Claude Opus 5.569.5%
  2. #72Granite 4.2 3B0.4%
  3. ~#74Olmo 3.1 32B InstructEstimated0.2%
  4. #74gpt-oss-120b0.2%
estimated from related benchmarks
~#63/80~1.5%Estimated
  1. #1Claude Opus 5.569.5%
  2. #60North Mini Code1.5%
  3. ~#63Ring-flash-2.0Estimated1.5%
  4. #63Trinity Large Thinking1.3%
estimated from related benchmarks
τ-Bench Banking (AA)
third-party
~last/89below measured range (<3.3%)Estimated
  1. #1Muse Spark 1.350.5%
  2. #88Llama 4 Scout3.3%
  3. ~#89Command AEstimated<3.3%
estimated from related benchmarks
~#89/89~3.1%Estimated
  1. #1Muse Spark 1.350.5%
  2. #88Llama 4 Scout3.3%
  3. ~#89Olmo 3.1 32B InstructEstimated3.1%
estimated from related benchmarks
~#70/89~6.9%Estimated
  1. #1Muse Spark 1.350.5%
  2. #68Qwen3.5 9B7.0%
  3. ~#70Ring-flash-2.0Estimated6.9%
  4. #70Ministral 3 14B6.6%
estimated from related benchmarks