AI model benchmarks and LLM leaderboard.

54 models from 14 labs, ranked on Artificial Analysis’s independent tests and LMArena’s blind votes, with list prices converted to Australian dollars and where each model can run in Australia. Snapshot: 2 Oct 2026. Use the results to shortlist models, then test them on your own work.

54 MODELS RANKEDA$1 = US$0.6949UPDATED 2 OCT 2026
OVERALL RANKING54 MODELS · 2 OCT 2026
54 MODELS
LLM leaderboard, ranked, as of 2 Oct 2026
MODELIN AUSTRALIA
01Claude Sonnet 5.5ANTHROPICPARTIAL96.356.0A$5.76GLOBAL
02Gemini 4 ArgonGOOGLE94.252.61525A$5.76NOT IN AU
03Claude Opus 5.5ANTHROPIC89.457.61504A$11.51IN AU
04GPT-6.1 SolOPENAIPARTIAL86.651.8A$5.76GLOBAL
05Claude Fable 5.1ANTHROPIC83.153.41501A$28.78#1GLOBAL
06Claude Fable 5ANTHROPIC80.649.61505A$28.78#9GLOBAL
07Claude Opus 5ANTHROPIC75.050.81491A$14.39#3IN AU
08Muse Spark 1.3META73.748.11495A$2.88#6NOT IN AU
09GPT-6 AstraOPENAI69.552.71476A$28.78#2GLOBAL
10Claude Opus 4.7ANTHROPIC68.740.71502A$14.39#17IN AU
11Step 5STEPFUNPARTIAL68.043.7A$2.05
12GPT-5.6 SolOPENAI66.847.01484A$11.51#7GLOBAL
13Gemini 3.8 FlashGOOGLE65.140.91494A$2.16#12GLOBAL
14Kimi K3MOONSHOT AI65.143.61488A$8.63#5GLOBAL
15MiMo V2.6 ProXIAOMI63.946.31480A$0.78NOT IN AU
16Muse Spark 1.2META63.639.61494A$2.88#20NOT IN AU
17Qwen3.8 MaxALIBABA63.545.41481A$4.32#4NOT IN AU
18GLM-5.3Z.AI62.144.81479A$3.09#10SELF-HOST
19Claude Opus 4.6ANTHROPIC60.531.91506A$14.39IN AU
20Gemini 3.7 FlashGOOGLE60.039.11488A$2.16#11GLOBAL
21Claude Opus 4.8ANTHROPIC59.641.81481A$14.39#15IN AU
22Qwen3.8 Flash NextALIBABAPARTIAL59.039.8A$0.33#13SELF-HOST
23GLM-5.3 FlashZ.AI55.741.81474A$0.34#16SELF-HOST
24GPT-5.5OPENAI55.738.41481A$16.19#18GLOBAL
25Muse Spark 1.1META55.633.71492A$2.88#23
26GPT-5.4OPENAI53.239.01475A$8.09#30IN AU
27GPT-6 SolOPENAI53.247.61456A$5.76GLOBAL
28DeepSeek V4.1 FlashDEEPSEEK52.639.51473A$0.76SELF-HOST
29GPT-5.6 TerraOPENAI51.742.11465A$6.48#14GLOBAL
30Gemini 3.6 FlashGOOGLE51.534.01483A$2.16#28GLOBAL
31Muse SparkMETA51.531.31489#37
32Gemini 3.1 ProGOOGLE48.629.71487A$6.48#32GLOBAL
33Grok 4.5XAI48.238.81466A$4.32#19NOT IN AU
34Grok 4.6XAI48.244.31453A$4.32#8GLOBAL
35GLM-5.2Z.AI47.233.71475A$3.09#21SELF-HOST
36Gemini 3.5 FlashGOOGLE46.832.61477A$4.86#29IN AU
37DeepSeek V4 FlashDEEPSEEKPARTIAL46.334.3A$0.95#24GLOBAL
38Gemini 3 ProGOOGLE45.828.01486A$6.48
39Claude Sonnet 5ANTHROPIC45.538.21462A$5.76#22IN AU
40Grok 4.7XAI45.146.41443A$4.32NOT IN AU
41DeepSeek V4 ProDEEPSEEK44.236.01464A$2.85#25GLOBAL
42Qwen3.7 MaxALIBABA42.029.51475A$5.40#31
43Claude Sonnet 4.6ANTHROPIC41.430.11472A$8.63#33IN AU
44GPT-5.6 LunaOPENAI40.137.31453A$0.65#26GLOBAL
45GPT-6 LunaOPENAI36.238.11444A$0.29GLOBAL
46MiMo V2.5 ProXIAOMI34.326.01467A$0.78#36SELF-HOST
47Kimi K2.6MOONSHOT AI32.227.01461A$2.46#34SELF-HOST
48Hy3TENCENT28.425.31457A$0.35#35SELF-HOST
49Qwen3.8 27BALIBABA28.433.71439A$1.62#27SELF-HOST
50MiniMax M3MINIMAX23.829.21440A$0.76#38SELF-HOST
51Gemini 3.5 Flash-LiteGOOGLE23.122.21454A$1.22#40GLOBAL
52GPT-5.4 miniOPENAI21.724.11447A$2.43#39
53Gemma 4 31BGOOGLE13.814.71453A$0.29#41SELF-HOST
54Mistral Medium 3.5MISTRAL AI0.014.21427A$4.32#42SELF-HOST

As of 2 Oct 2026, Claude Sonnet 5.5 leads, ahead of Gemini 4 Argon and Claude Opus 5.5, out of 54 ranked models. The highest-ranked open-weights model is Kimi K3 (14th). The cheapest model in the top ten is Muse Spark 1.3, at A$2.88 per million tokens.

DATA SOVEREIGNTY

Where you can run them in Australia.

9 of the 54 models we track can run with requests processed in Australia on at least one major cloud platform — mostly Claude, through AWS Bedrock in Sydney and Melbourne. The rest are reached through global routing, or self-hosted if the weights are open.

AUSTRALIAN AVAILABILITY
HOW THIS RANKING WORKS

What goes into the overall score.

Half the score is Artificial Analysis’s Intelligence Index (independent tests), half is LMArena’s text rating (which answers people prefer in blind votes). Scores from tests and votes don’t always agree, so using both gives a steadier ranking than either alone. New models often appear in one source a week or two before the other; they are ranked on what’s available and marked partial.

50%AA Intelligence Index

Artificial Analysis’s composite of its independent evaluations: reasoning, knowledge, maths, coding, long context and agent tasks.

50%LMArena Text

People compare two anonymous answers to the same prompt and vote for the better one. Style-controlled, so longer or more heavily formatted answers don’t win on looks alone.

Scores are rescaled 0–100 across the models we track, so they compare models with each other rather than against a fixed bar. Full methodology →

QUESTIONS

What people ask about AI model rankings.

As of 2 Oct 2026, Claude Sonnet 5.5 ranks first, followed by Gemini 4 Argon and Claude Opus 5.5. The ranking combines AA Intelligence Index and LMArena Text and is refreshed weekly.

Kimi K3 from Moonshot AI is the highest-ranked open-weights model (14th of 54). Open weights can be run on your own infrastructure, including in an Australian region.

Of the top ten, Muse Spark 1.3 is cheapest at A$2.88 per million tokens (blended), against A$28.78 for Claude Fable 5.1. Prices are list prices converted at A$1 = US$0.6949, excluding GST.

Of the top ten, Claude Opus 5.5, Claude Opus 5 and Claude Opus 4.7 can run with requests kept in Australia on at least one major cloud platform. See the Australia page for each platform.

Half the score is Artificial Analysis’s Intelligence Index (independent tests), half is LMArena’s text rating (which answers people prefer in blind votes). Scores from tests and votes don’t always agree, so using both gives a steadier ranking than either alone. New models often appear in one source a week or two before the other; they are ranked on what’s available and marked partial. Each input is rescaled 0–100 across the models we track, then weighted: AA Intelligence Index 50% and LMArena Text 50%.

PUT THE COMPARISON TO WORK

Need help choosing and using AI for your business?