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.
Phi-4Gemini Omni FlashGemini Omni 1.1 FlashWan 3.0Up to 4 models — remove one to add another.

Overview

Metric
Phi-4
Gemini Omni Flash
Gemini Omni 1.1 Flash
Wan 3.0
Lab
Microsoft AI
Google DeepMind
Google DeepMind
Alibaba Qwen
Released
Dec 12, 2024
May 19, 2026
Aug 27, 2026
Aug 19, 2026
Weights
Open
Proprietary
Proprietary
Proprietary
Input price
$/M tok
$0.125
—
—
—
Output price
$/M tok
$0.50
—
—
—
Blended price
$/M tok · 3:1 in:out
$0.219
—
—
—
Output speed
tok/s
40
—
—
—
Context
tokens
16K
—
—
—
Price per second
1080p
—
$0.10Best
$0.10Best
$0.20

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
Phi-4
Gemini Omni Flash
Gemini Omni 1.1 Flash
Wan 3.0
Writing & chat
5.8±4.2
#145/146Verified
Not ranked
Not ranked
Not ranked
Hard reasoning
20.2±5.8
#136/182Verified
Not ranked
Not ranked
Not ranked
Agents
13.9±10.0
#166/173Verified
Not ranked
Not ranked
Not ranked
Video generation
Not ranked
96.9±3.0Best
#1/34Verifiedbest value
94.3±6.3
#2/34Verified
93.8±4.1
#3/34Verified

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
Phi-4
Gemini Omni Flash
Gemini Omni 1.1 Flash
Wan 3.0
IFBench
day 0
#118/12523.5%Verified
  1. #1MiniMax-M382.9%
  2. #117Granite 4.0 Micro24.8%
  3. #118Phi-423.5%
  4. #119Apertus 8B Instruct22.4%
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. ~#5Phi-4Estimated<81.3%
estimated from related benchmarks
—
—
—
LMArena Text, Non-English (Elo)
third-party
#52/531233Verified
  1. #1Claude Opus 5.51501
  2. #51NVIDIA Nemotron 3 Nano 30B A3B1286
  3. #52Phi-41233
  4. #53Olmo 3.1 32B Think1231
lmarena.ai · 2026-09-13
—
—
—
LMArena Text (Elo)
third-party
#53/531256Verified
  1. #1Claude Opus 5.51509
  2. #52Olmo 3.1 32B Think1286
  3. #53Phi-41256
lmarena.ai · 2026-09-13
—
—
—
EQ-Bench Creative Writing v3 (Elo)
third-party
~#24/26~1147Estimated
  1. #1GPT-6 Astra2173
  2. #23Gemma 4 31B1368
  3. ~#24Phi-4Estimated1147
  4. #24gpt-oss-120b961
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
Phi-4
Gemini Omni Flash
Gemini Omni 1.1 Flash
Wan 3.0

Agents benchmarks

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

Metric
Phi-4
Gemini Omni Flash
Gemini Omni 1.1 Flash
Wan 3.0
τ²-bench (Telecom)
day 0
#106/1150.0%Verified
  1. #1Step 3.7 Flash98.5%
  2. #106Olmo 3.1 32B Think0.0%
  3. #106Phi-40.0%
  4. #106Reka Flash 30.0%
artificialanalysis.ai · 2026-09-24
—
—
—
OSWorld-Verified
day 0
~#11/12~62.4%Estimated
  1. #1Kimi K384.8%
  2. #10Muse Glimmer65.9%
  3. ~#11Phi-4Estimated62.4%
  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. ~#3Phi-4Estimated53.8%
  4. #3GPT-5.6 Terra50.2%
estimated from related benchmarks
—
—
—
BrowseComp
day 0
~#17/18~33.0%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #16Nemotron 3 Ultra44.4%
  3. ~#17Phi-4Estimated33.0%
  4. #17Mistral Small 421.3%
estimated from related benchmarks
—
—
—
GDPval-AA (Elo)
third-party
~#59/87~581Estimated
  1. #1Claude Opus 5.51846
  2. #58gpt-oss-120b596
  3. ~#59Phi-4Estimated581
  4. #59Granite 4.2 30B564
estimated from related benchmarks
—
—
—
AutomationBench-AA
third-party
~#80/80~0.2%Estimated
  1. #1Claude Opus 5.569.5%
  2. #74Magistral Small 1.20.2%
  3. ~#80Phi-4Estimated0.2%
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. ~#89Phi-4Estimated<3.3%
estimated from related benchmarks
—
—
—

Video generation benchmarks

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

Metric
Phi-4
Gemini Omni Flash
Gemini Omni 1.1 Flash
Wan 3.0
AA Text-to-Video Arena
third-party
—
#2/251332Verified
  1. #1Wan 3.0Few votes1335
  2. #2Gemini Omni Flash1332
  3. #3MiniMax H31302
artificialanalysis.ai · 2026-09-24
~#3/26~1310Estimated
  1. #1Wan 3.0Few votes1335
  2. #2Gemini Omni Flash1332
  3. ~#3Gemini Omni 1.1 FlashEstimated1310
  4. #3MiniMax H31302
estimated from related benchmarks
#1/251335BestVerifiedFew votes
  1. #1Wan 3.0Few votes1335
  2. #2Gemini Omni Flash1332
artificialanalysis.ai · 2026-09-24
AA Image-to-Video Arena
third-party
—
#1/261369BestVerified
  1. #1Gemini Omni Flash1369
  2. #2Wan 3.0Few votes1361
artificialanalysis.ai · 2026-09-24
~#4/27~1353Estimated
  1. #1Gemini Omni Flash1369
  2. #3MiniMax H31357
  3. ~#4Gemini Omni 1.1 FlashEstimated1353
  4. #4Seedance 2.01340
estimated from related benchmarks
#2/261361VerifiedFew votes
  1. #1Gemini Omni Flash1369
  2. #2Wan 3.0Few votes1361
  3. #3MiniMax H31357
artificialanalysis.ai · 2026-09-24
AA Text-to-Video Arena (with audio)
third-party
—
#1/221233BestVerified
  1. #1Gemini Omni Flash1233
  2. #2Wan 3.01230
artificialanalysis.ai · 2026-09-24
~#3/23~1221Estimated
  1. #1Gemini Omni Flash1233
  2. #2Wan 3.01230
  3. ~#3Gemini Omni 1.1 FlashEstimated1221
  4. #3MiniMax H31220
estimated from related benchmarks
#2/221230Verified
  1. #1Gemini Omni Flash1233
  2. #2Wan 3.01230
  3. #3MiniMax H31220
artificialanalysis.ai · 2026-09-24
AA Image-to-Video Arena (with audio)
third-party
—
#2/231177BestVerified
  1. #1MiniMax H31181
  2. #2Gemini Omni Flash1177
  3. #3HiDream-O1-VideoFew votes1176
artificialanalysis.ai · 2026-09-24
~#5/24~1173Estimated
  1. #1MiniMax H31181
  2. #4Seedance 2.01174
  3. ~#5Gemini Omni 1.1 FlashEstimated1173
  4. #5Wan 3.01164
estimated from related benchmarks
#5/231164Verified
  1. #1MiniMax H31181
  2. #4Seedance 2.01174
  3. #5Wan 3.01164
  4. #6HappyHorse-1.11106
artificialanalysis.ai · 2026-09-24
LMArena Text-to-Video
third-party
—
#2/171513Verified
  1. #1Gemini Omni 1.1 FlashFew votes1516
  2. #2Gemini Omni Flash1513
  3. #3FLUX 3 VideoFew votes1493
arena.ai · 2026-09-21
#1/171516BestVerifiedFew votes
  1. #1Gemini Omni 1.1 FlashFew votes1516
  2. #2Gemini Omni Flash1513
arena.ai · 2026-09-21
#5/171476VerifiedFew votes
  1. #1Gemini Omni 1.1 FlashFew votes1516
  2. #4Seedance 2.01479
  3. #5Wan 3.0Few votes1476
  4. #6Seedance 2.51474
arena.ai · 2026-09-21
LMArena Image-to-Video
third-party
—
#6/191465Verified
  1. #1MiniMax H31495
  2. #5Seedance 2.01475
  3. #6Gemini Omni Flash1465
  4. #7Grok Imagine Video 1.51456
arena.ai · 2026-09-21
#2/191488BestVerifiedFew votes
  1. #1MiniMax H31495
  2. #2Gemini Omni 1.1 FlashFew votes1488
  3. #3Wan 3.0Few votes1480
arena.ai · 2026-09-21
#3/191480VerifiedFew votes
  1. #1MiniMax H31495
  2. #2Gemini Omni 1.1 FlashFew votes1488
  3. #3Wan 3.0Few votes1480
  4. #4Seedance 2.51477
arena.ai · 2026-09-21
VBench
day 0
—
—
—
—