AI model leaderboard

Text, image and video models ranked on one page, on published third-party scores. The text table is every model the official plan serves; image and video are the boards themselves, with the models OHarness sells marked.

OHarness runs no model evaluations. Every score is copied from a published third-party board, cited per table with the date it was read — 21 of the 65 models on the official plan carry one, and the rest show a dash rather than an estimate. The model list comes from the gateway that serves them, so nothing here advertises a model you cannot call. Last read 2026-09-16.

Claude Fable 5.1
Top text model · 53 Intelligence Index
GPT Image 2.5 Flare
Top image model · 1189 Arena Elo
Seedance 2.5
OHarness pick · 1482 Arena Elo

Ranked by modality

Scores only mean something within a modality — an intelligence index and an Elo rating measure different things by different methods — so each table ranks only against itself. Sort any column.

Text

Every model the official plan serves, scored by the index. Sort by either column.

Text models ranked by quality. Every model the official plan serves, scored by the index. Sort by either column.
#Model
1Claude Fable 5.1Anthropic5365 t/s
2Gemini 4 Argon1Google Gemini5385 t/s
3GPT-6 AstraOpenAI5353 t/s
4Claude Opus 5Anthropic5149 t/s
5Claude Fable 5Anthropic5065 t/s
6GPT-5.6 SolOpenAI4765 t/s
7DeepSeek V4.1 Flash 10172DeepSeek45216 t/s
8GLM 5.3Z.ai (GLM)4567 t/s
9Grok 4.6xAI4458 t/s
10Kimi K3Moonshot (Kimi)4435 t/s
11GPT-5.6 TerraOpenAI4299 t/s
12Gemini 3.8 FlashGoogle Gemini41332 t/s
13Qwen3.8 MaxQwen (Alibaba Cloud)4040 t/s
14Gemini 3.7 FlashGoogle Gemini39289 t/s
15Grok 4.5xAI3960 t/s
16Claude Sonnet 5Anthropic3880 t/s
17GPT-5.6 LunaOpenAI38115 t/s
18GLM 5.2Z.ai (GLM)3471 t/s
19DeepSeek V4 ProDeepSeek3186 t/s
20Gemini 3.1 Pro Preview3Google Gemini30108 t/s
21Claude Haiku 4.5Anthropic1885 t/s
22Claude Fable 5.2Anthropic——
23Claude Haiku 5.5Anthropic——
24Claude Opus 4.8Anthropic——
25Claude Opus 5.5Anthropic——
26Claude Sonnet 5.5Anthropic——
27DeepSeek V4 FlashDeepSeek——
28DeepSeek V4 Pro 0813DeepSeek——
29DeepSeek V4.1 FlashDeepSeek——
30Gemini 2.5 FlashGoogle Gemini——
31Gemini 3.1 Flash-LiteGoogle Gemini——
32Gemini 3.5 FlashGoogle Gemini——
33Gemini 3.5 Flash-LiteGoogle Gemini——
34Gemini 4 CarbonGoogle Gemini——
35GLM 5.3 FlashZ.ai (GLM)——
36GPT-4oOpenAI——
37GPT-5.2OpenAI——
38GPT-5.4OpenAI——
39GPT-5.4 miniOpenAI——
40GPT-5.4 nanoOpenAI——
41GPT-5.5OpenAI——
42GPT-6 Astra ProOpenAI——
43GPT-6 LunaOpenAI——
44GPT-6 Luna ProOpenAI——
45GPT-6 SolOpenAI——
46GPT-6 Sol ProOpenAI——
47GPT-6.1 SolOpenAI——
48GPT-6.1 Sol ProOpenAI——
49GPT-6.1 TerraOpenAI——
50GPT-6.1 Terra ProOpenAI——
51Grok 4.7xAI——
52Kimi K2 0711Moonshot (Kimi)——
53Kimi K2 0905Moonshot (Kimi)——
54Kimi K2 ThinkingMoonshot (Kimi)——
55Kimi K2.5Moonshot (Kimi)——
56Kimi K2.6Moonshot (Kimi)——
57Kimi K2.7 CodeMoonshot (Kimi)——
58Kimi K3.1 ProMoonshot (Kimi)——
59MiMo V2.6 Flashxiaomi——
60MiMo V2.6 Proxiaomi——
61Muse Spark 1.3meta——
62Muse Wondermeta——
63Qwen3.8 FlashQwen (Alibaba Cloud)——
64Sonar Deep ResearchPerplexity——
65Video UnderstandingOttoPort——
  1. 1Gemini 4 Argon Scored at high reasoning effort.
  2. 2DeepSeek V4.1 Flash 1017 Scored at max reasoning effort.
  3. 3Gemini 3.1 Pro Preview Scored as Gemini 3.1 Pro; the served entry is the preview build of the same model.

Image

Text-to-image models, ranked by blind head-to-head votes. The ones marked On OHarness generate from the same credits as chat — prices are on the pricing page.

Image models ranked by quality. Text-to-image models, ranked by blind head-to-head votes. The ones marked On OHarness generate from the same credits as chat — prices are on the pricing page.
#Model
1GPT Image 2.5 Flare1On OHarnessOpenAI1189
2GPT Image 2.52On OHarnessOpenAI1183
3GPT Image 23On OHarnessOpenAI1173
4Nano Banana 2On OHarnessGoogle1122
5GPT Image 1.54On OHarnessOpenAI1104
6Nano Banana ProOn OHarnessGoogle1099
7Nano Banana LiteOn OHarnessGoogle1088
8Qwen Image 3.0 ProOn OHarnessAlibaba1087
9Seedream 5.0 ProByteDance1082
10Qwen Image 3.0On OHarnessAlibaba1073
11Seedream 5.0 LiteOn OHarnessByteDance1000
12Wan 2.7 ProOn OHarnessAlibaba979
13GPT Image 1 Mini5On OHarnessOpenAI919
14Midjourney v76On OHarnessMidjourney897
  1. 1GPT Image 2.5 Flare Ranked at the max quality setting.
  2. 2GPT Image 2.5 Board entry: GPT Image 2.5 Sunburst, max quality.
  3. 3GPT Image 2 Ranked at the high quality setting.
  4. 4GPT Image 1.5 Ranked at the high quality setting.
  5. 5GPT Image 1 Mini Ranked at the medium quality setting.
  6. 6Midjourney v7 Board entry: Midjourney v7 Alpha.

Video

Text-to-video models, ranked by blind head-to-head votes. The ones marked On OHarness generate from the same credits as chat — prices are on the pricing page.

Video models ranked by quality. Text-to-video models, ranked by blind head-to-head votes. The ones marked On OHarness generate from the same credits as chat — prices are on the pricing page.
#Model
1Seedance 2.51OHarness pickOn OHarnessByteDance1482
2Gemini Omni 1.1 FlashOn OHarnessGoogle1515
3Gemini Omni FlashOn OHarnessGoogle1511
4FLUX 3 VideoOn OHarnessBlack Forest Labs1494
5Wan 3.02On OHarnessAlibaba1494
6Seedance 2.03On OHarnessByteDance1479
7MiniMax H3On OHarnessMiniMax1462
8Veo 3.14On OHarnessGoogle1364
9Veo 3.1 Fast5On OHarnessGoogle1362
10Wan 2.7On OHarnessAlibaba1341
11Wan 2.6On OHarnessAlibaba1328
12Wan 2.56On OHarnessAlibaba1246
13Hailuo 2.3On OHarnessMiniMax1205
14Hailuo 027On OHarnessMiniMax1181

Seedance 2.5 is placed first by OHarness, not by the board. OHarness places it first; the board does not. ByteDance's current flagship — native 30-second clips, 4K, up to 50 reference images — and the one model in this table whose measured Elo is visibly still catching up to it: arena.ai has it fifth at 1482, and Artificial Analysis has not scored it at all, because both boards are accumulating votes on a model that shipped after they last settled. The 1482 in its row is the board's number, unchanged. Only the position is ours.

  1. 1Seedance 2.5 Board entry: dreamina-seedance-2.5-720p. Not yet ranked by Artificial Analysis.
  2. 2Wan 3.0 Board entry: wan3.0. The Prime tier is not separately ranked.
  3. 3Seedance 2.0 Board entry: dreamina-seedance-2.0-720p.
  4. 4Veo 3.1 Board entry: veo-3.1-audio at 720p; the 1080p entry scores 1363.
  5. 5Veo 3.1 Fast Board entry: veo-3.1-fast-audio at 720p.
  6. 6Wan 2.5 Board entry: wan2.5-t2v-preview.
  7. 7Hailuo 02 Board entry: hailuo-02-standard; the Pro tier scores 1198.

How these rankings are built

Quality and speed: not ours

Text models carry the Artificial Analysis Intelligence Index; image and video carry Arena Elo from blind head-to-head votes. Elo pools are not interchangeable, so each column comes from exactly one board, named with the date it was read. The logos are their owners’ trademarks, here to identify the models beside them.

No prices, on purpose

A money column on a page about which model is best asks the reader to weigh two different questions in one row, and they get a worse answer to both. What each model costs — both rates, per million tokens, as the gateway meters them — is on the pricing page, which is a rate card and says so.

Picks: the one opinion here

Boards lag the market — a model can ship, lead its category, and wait months for an arena to gather enough votes to rank it. Where that happens the model is pinned to the top of the default view, badged, with the reason printed under the table. A pin never writes a score into a cell, and it disappears the moment you reverse the sort.

Image and video: the boards, marked

Both tables are the published boards in their own order. A row tagged On OHarness is a model the official plan sells today, from the same credits as chat; the tag is set from the gateway's own list, so a model it stops selling loses it. Rates are on the pricing page, not here.

Questions

Who produced these scores?

Nobody here. Every quality figure is copied from a published third-party leaderboard, cited per table with the date it was read. OHarness sells access to some of these models, and a ranking from a seller is only worth reading if it says which numbers it measured and which it copied. It measured none of them.

Can I use the image and video models through OHarness?

Yes — the rows marked On OHarness. They generate from the same credits as chat, in the app or through the API; the per-image and per-second rates are on the pricing page. The rest of each table is the board as published, so the field is visible even where OHarness does not sell a model.

Why is there no price column?

Because it would make both questions harder to answer. Which model is best and what it costs are separate decisions, and a table that mixes them nudges the reader into ranking by money without saying so. The rate card is on the pricing page, where every model is listed at both rates, fetched from the gateway that meters the call.

Why is a model I use missing?

Either the plan does not serve it, or no board had published a score for it when this table was last read. A model with no score still appears in the text table with a dash: it is a model you can call, and an estimate in that cell would be worth less than the blank.

Why is a model ranked above one with a higher score?

Because it is pinned, and the badge on the row says so. It is the only judgement on this page: arenas lag the market, and a model can lead its category for months before a board has the votes to rank it there. A pin moves a row and nothing else — the score in the cell is still the board's, the reason is printed under the table, and reversing the sort drops the pin entirely.

Can I compare the numbers across tables?

No, and nothing on this page does. Text carries an intelligence index out of roughly a hundred; image and video carry Arena Elo, which has no meaningful zero and comes from a separate pool of votes per board. The scores rank within a table and mean nothing between them.