Skip to content

Rank 270+ AI models by the job

Pick a scenario, drag the weights, set a budget. Free, ad-free and built on open data.

  • Models ranked

    267

  • Benchmarks

    38

  • Scenarios

    14

  • Last refresh

    16 Nov 2026

Leaderboard

Each scenario weights benchmarks differently. Switch between them and the leaderboard re-ranks live.

Build your own

A pair-programming assistant for IDE / agent loops. Heavy on coding benchmarks, with a real-world agentic component (SWE-bench) and some weight on cost since coding loops burn tokens. A small slice goes to the recovery-rate reliability axis because real-world agent loops live or die on whether the model self-corrects.Scores here rest on a median 25% of this scenario's benchmark weight; 10 of 185 models have 80% or more. See the evidence map.

Showing the top 50 of 76 models, sorted by scenario score, descending.

Shortlist and details
1
Google
vision
80.450% cov.
$201.0M14921.5—————
2
Google
vision
80.130% cov.
$691.0M44.54.30$4.3164.2———
3
Google
vision
78.750% cov.
$782.0M39.04.47—————
4
Google
vision
78.030% cov.
$261.0M1104.36$6.2619.0———
5
MiniMax
76.740% cov.
$18198k1524.90——————
6
Anthropic
vision
76.630% cov.
$2761.0M11.34.27$2.4581.1———
7
Zhipu AI (GLM)
75.640% cov.
$34200k80.44.18——————
8
DeepSeek
74.970% cov.
$31128k86.84.36————
9
OpenAI
vision
74.630% cov.
$81.1M3258.51$0.3357.8———
10
OpenAI
vision
74.330% cov.
$691.1M40.95.44$0.3635.7———
11
DeepSeek
74.230% cov.
$41.0M61913.0—37.5———
12
Anthropic
vision
73.530% cov.
$1381.0M20.910.1$0.7839.1———
13
DeepSeek
73.455% cov.
$17128k1495.16—————
14
OpenAI
vision
73.365% cov.
$120400k24.12.64————
15
OpenAI
vision
72.830% cov.
$31.1M6755.77$0.0435.7———
16
OpenAI
vision
72.750% cov.
$84400k33.54.52—————
17
Anthropic
vision
72.655% cov.
$345200k8.626.94—19.7——
18
Google
vision
72.4
$602.0M45.83.76———
19
Zhipu AI (GLM)
72.450% cov.
$53205k50.57.42—————
20
Alibaba (Qwen)
72.440% cov.
$16262k1545.75——————
21
Alibaba (Qwen)
72.070% cov.
$11131k2334.49————
22
Zhipu AI (GLM)
71.940% cov.
$34131k75.84.19——————
23
OpenAI
vision
71.830% cov.
$781.1M35.28.82$3.7333.2———
24
Anthropic
vision
71.850% cov.
$345200k8.524.26—————
25
OpenAI
71.7
$66200k40.73.63———
26
Moonshot (Kimi)
71.265% cov.
$34256k74.811.1————
27
Anthropic
vision
71.030% cov.
$6901.0M4.366.04$5.5630.4———
28
OpenAI
vision
70.330% cov.
$195400k14.44.89—38.6———
29
OpenAI
70.2
$120200k22.57.35———
30
OpenAI
vision
69.830% cov.
$1381.1M19.76.26—39.3———
31
Zhipu AI (GLM)
69.530% cov.
$731.0M35.37.52$1.5717.7———
32
OpenAI
vision
69.430% cov.
$3451.1M8.234.29$2.7334.5———
33
OpenAI
vision
69.250% cov.
$60400k43.51.71—————
34
Anthropic
vision
68.950% cov.
$207200k13.23.31—————
35
Anthropic
vision
68.430% cov.
$3451.0M8.106.89$11.8213.4———
36
Anthropic
vision
68.130% cov.
$345200k8.063.50—38.5———
37
Moonshot (Kimi)
vision
66.930% cov.
$1381.0M18.83.60$3.6820.7———
38
OpenAI
vision
66.730% cov.
$691.1M36.14.99$2.4737.6———
39
OpenAI
vision
65.150% cov.
$12400k1833.52—————
40
Anthropic
vision
63.750% cov.
$69200k34.32.21$0.53————
41
Anthropic
vision
62.430% cov.
$1381.0M17.49.35—16.7———
42
Google
vision
62.230% cov.
$151.0M1429.40$0.690.0———
43
DeepSeek
61.7
$17128k12012.3———
44
xAI
61.470% cov.
—1.0M——————
45
OpenAI
vision
61.240% cov.
$98400k23.86.00—————
46
Anthropic
vision
60.930% cov.
$3451.0M7.161.66—9.2———
47
Anthropic
vision
60.930% cov.
$207200k11.66.62—20.1———
48
xAI
vision
60.840% cov.
$345256k7.153.23—————
49
Google
vision
59.6
$151.0M1344.48———
50
OpenAI
57.4
$66200k31.45.66———
Showing the top 50 of 76 models.
Scenario score
weighted benchmark average, 0–100; blended with cost when the scenario weights cost
Score/$
score per blended $/M tokens (3 in : 1 out)
Score/s
score per second for a 500-token answer
Stability
consistency of repeated answers, from an independent monitor
% cov.
share of the benchmark weight with data
high contamination risk
saturated benchmark
think
reasoning-effort variant of the same model

Showing 76 of 267 models. Tap or hover any score for the raw value, its date and contamination risk. Click a model for its full profile.

Cost vs quality

Models on the Pareto frontier (highlighted) give you the best quality at their cost tier.

Loading chart…

Shortlists

Highest Analyzer Index; effort variants of the same model count once.