AI Model Ranking
Top 50 from Artificial Analysis.
Snapshot: 2026-10-03 · Last reviewed: 2026-10-03
Metrics follow a snapshot of the Artificial Analysis public LLM leaderboard: Intelligence Index, cost per task, and speed reflect benchmark performance at the snapshot date. Provider pricing, availability, and rankings change frequently, and a high benchmark score does not guarantee the best result for a specific codebase or workflow.
Current reasoning model
Claude Opus 5.5 max leads this snapshot at Intelligence Index 58 with 1M context and cost per task $5.98. Median speed is 93 tok/s, and first chunk is 689.18s.
Best for: Highest-effort Claude Opus work when the top Intelligence Index matters more than a short first chunk.
Anthropic
Current reasoning model
Claude Sonnet 5.5 max is #2 at Intelligence Index 56 with 1M context. Cost per task is $7.67, the highest in the top 10, and first chunk is 428.36s.
Best for: Highest-effort Claude Sonnet work when Intelligence Index matters more than task cost and wait time.
Anthropic
Current reasoning model
Claude Opus 5.5 xhigh ties Sonnet 5.5 max at Intelligence Index 56 with 1M context and cost per task $3.46. First chunk is 140.81s, shorter than Sonnet 5.5 max.
Best for: High-effort Opus 5.5 coding when you want the same Intelligence Index as Sonnet 5.5 max at a lower task cost.
Anthropic
Current reasoning model
Claude Opus 5.5 high is #4 at Intelligence Index 54 with 1M context. Cost per task is $1.82 and first chunk is 37.37s, far below Opus 5.5 xhigh.
Best for: Claude Opus 5.5 coding that still needs a high Intelligence Index without the xhigh first-chunk wait.
Anthropic
Current reasoning model
Claude Fable 5.1 max is #5 at Intelligence Index 53 with 1M context. Cost per task is $7.63, just under Sonnet 5.5 max, and first chunk is 186.52s.
Best for: Highest-effort Claude Fable work when Intelligence Index matters more than task cost and wait time.
Anthropic
Current reasoning model
Claude Fable 5.1 xhigh stays at Intelligence Index 53, tied with Fable 5.1 max, with 1M context and cost per task $5.98. First chunk is 96.75s, shorter than Fable 5.1 max.
Best for: High-effort Fable 5.1 coding when max task cost is too high and you still want the same Intelligence Index.
Anthropic
Current reasoning model
GPT-6 Astra max is #7 at Intelligence Index 53 with 1M context. Cost per task is $3.26, below Fable 5.1 max, and first chunk is 319.00s.
Best for: OpenAI-centered frontier agents that can absorb a very long first-chunk delay.
OpenAI
Current model; partial public metrics
Gemini 4 Argon high is #8 at Intelligence Index 53 with 1M context and cost per task $1.99, tied with several models at 53. Output speed and latency are not published yet.
Best for: Google frontier coding when Intelligence Index matters more than published speed.
Current reasoning model
GPT-6 Astra xhigh is #9 at Intelligence Index 52, 1M context, and cost per task $2.31. First chunk is 144.37s, shorter than Astra max.
Best for: OpenAI coding agents that need near-max Astra quality at a lower task cost than max.
OpenAI
Current reasoning model
Claude Sonnet 5.5 xhigh is #10 at Intelligence Index 52 with 1M context. Cost per task is $2.75, median speed is 104 tok/s, and first chunk is 33.63s, far below Sonnet 5.5 max.
Best for: Claude Sonnet 5.5 coding that still needs a high Intelligence Index without the max first-chunk wait.
Anthropic
Current reasoning model
OpenAI GPT Sol 6.1 (max) ranks in this snapshot with Intelligence Index 52, 1M context, cost per task $0.72, median 57 tok/s, and first chunk 282.35s.
Best for: OpenAI coding agents, long-context work, and snapshot-based model comparison.
OpenAI
Current reasoning model
Anthropic Claude Opus 5.5 (medium) ranks in this snapshot with Intelligence Index 51, 1M context, cost per task $1.34, median 73 tok/s, and first chunk 25.24s.
Best for: Anthropic coding agents, long-context work, and snapshot-based model comparison.
Anthropic
Current reasoning model
Anthropic Claude Fable 5.1 (high) ranks in this snapshot with Intelligence Index 51, 1M context, cost per task $3.91, median 56 tok/s, and first chunk 25.00s.
Best for: Anthropic coding agents, long-context work, and snapshot-based model comparison.
Anthropic
Current reasoning model
OpenAI GPT Sol 6.1 (xhigh) ranks in this snapshot with Intelligence Index 51, 1M context, cost per task $0.39, median 51 tok/s, and first chunk 128.47s.
Best for: OpenAI coding agents, long-context work, and snapshot-based model comparison.
OpenAI
Current reasoning model
OpenAI GPT Astra 6 (high) ranks in this snapshot with Intelligence Index 51, 1M context, cost per task $1.73, median 48 tok/s, and first chunk 65.56s.
Best for: OpenAI coding agents, long-context work, and snapshot-based model comparison.
OpenAI
Current reasoning model
OpenAI GPT Sol 6.1 (high) ranks in this snapshot with Intelligence Index 50, 1M context, cost per task $0.32, median 50 tok/s, and first chunk 57.71s.
Best for: OpenAI coding agents, long-context work, and snapshot-based model comparison.
OpenAI
Current reasoning model
OpenAI GPT Astra 6 (medium) ranks in this snapshot with Intelligence Index 50, 1M context, cost per task $1.54, median 46 tok/s, and first chunk 4.70s.
Best for: OpenAI coding agents, long-context work, and snapshot-based model comparison.
OpenAI
Current reasoning model
Anthropic Claude Fable 5.1 (medium) ranks in this snapshot with Intelligence Index 49, 1M context, cost per task $2.98, median 57 tok/s, and first chunk 9.11s.
Best for: Anthropic coding agents, long-context work, and snapshot-based model comparison.
Anthropic
Current reasoning model
Meta Muse Spark 1.3 (max) ranks in this snapshot with Intelligence Index 48, 1M context, cost per task $1.60, median 135 tok/s, and first chunk 52.46s.
Best for: Meta coding agents, long-context work, and snapshot-based model comparison.
Meta
Current reasoning model
OpenAI GPT Sol 6.1 (medium) ranks in this snapshot with Intelligence Index 48, 1M context, cost per task $0.21, median 45 tok/s, and first chunk 5.29s.
Best for: OpenAI coding agents, long-context work, and snapshot-based model comparison.
OpenAI
Current reasoning model
Anthropic Claude Fable 5.1 (low) ranks in this snapshot with Intelligence Index 47, 1M context, cost per task $2.37, median 55 tok/s, and first chunk 4.73s.
Best for: Anthropic coding agents, long-context work, and snapshot-based model comparison.
Anthropic
Current reasoning model
Anthropic Claude Sonnet 5.5 (high) ranks in this snapshot with Intelligence Index 47, 1M context, cost per task $1.12, median 102 tok/s, and first chunk 12.19s.
Best for: Anthropic coding agents, long-context work, and snapshot-based model comparison.
Anthropic
Current reasoning model
SpaceXAI Grok 4.7 (xhigh) ranks in this snapshot with Intelligence Index 46, 500k context, cost per task $3.74, median 79 tok/s, and first chunk 41.26s.
Best for: SpaceXAI coding agents, long-context work, and snapshot-based model comparison.
SpaceXAI
Current reasoning model
SpaceXAI Grok 4.7 (high) ranks in this snapshot with Intelligence Index 46, 500k context, cost per task $2.73, median 78 tok/s, and first chunk 33.12s.
Best for: SpaceXAI coding agents, long-context work, and snapshot-based model comparison.
SpaceXAI
Current reasoning model
Xiaomi MiMo V2.6 Pro ranks in this snapshot with Intelligence Index 46, 1M context, cost per task $0.13, median 45 tok/s, and first chunk 3.82s.
Best for: Xiaomi coding agents, long-context work, and snapshot-based model comparison.
Xiaomi
Current reasoning model
OpenAI GPT Astra 6 (low) ranks in this snapshot with Intelligence Index 46, 1M context, cost per task $0.82, median 47 tok/s, and first chunk 2.75s.
Best for: OpenAI coding agents, long-context work, and snapshot-based model comparison.
OpenAI
Current reasoning model
Alibaba Qwen 3.8 Max (0902) ranks in this snapshot with Intelligence Index 45, 984k context, cost per task $5.41, median 38 tok/s, and first chunk 2.67s.
Best for: Alibaba coding agents, long-context work, and snapshot-based model comparison.
Alibaba
Current reasoning model
Meta Muse Spark 1.3 (xhigh) ranks in this snapshot with Intelligence Index 45, 1M context, cost per task $1.37, median 146 tok/s, and first chunk 41.50s.
Best for: Meta coding agents, long-context work, and snapshot-based model comparison.
Meta
Current reasoning model
Z AI GLM 5.3 (max) ranks in this snapshot with Intelligence Index 45, 1M context, cost per task $2.01, median 74 tok/s, and first chunk 3.18s.
Best for: Z AI coding agents, long-context work, and snapshot-based model comparison.
Z AI
Current reasoning model
StepFun Step 5 Preview ranks in this snapshot with Intelligence Index 44, 1M context, cost per task $0.72, median 85 tok/s, and first chunk 3.03s.
Best for: StepFun coding agents, long-context work, and snapshot-based model comparison.
StepFun
Current reasoning model
Kimi Kimi K3 (max) ranks in this snapshot with Intelligence Index 44, 1.05M context, cost per task $2.00, median 36 tok/s, and first chunk 4.12s.
Best for: Kimi coding agents, long-context work, and snapshot-based model comparison.
Kimi
Current reasoning model
Anthropic Claude Opus 5.5 (low) ranks in this snapshot with Intelligence Index 42, 1M context, cost per task $0.55, median 80 tok/s, and first chunk 9.94s.
Best for: Anthropic coding agents, long-context work, and snapshot-based model comparison.
Anthropic
Current reasoning model
SpaceXAI Grok 4.7 (low) ranks in this snapshot with Intelligence Index 42, 500k context, cost per task $1.25, median 75 tok/s, and first chunk 8.62s.
Best for: SpaceXAI coding agents, long-context work, and snapshot-based model comparison.
SpaceXAI
Current reasoning model
OpenAI GPT Sol 6.1 (low) ranks in this snapshot with Intelligence Index 42, 1M context, cost per task $0.13, median 48 tok/s, and first chunk 3.37s.
Best for: OpenAI coding agents, long-context work, and snapshot-based model comparison.
OpenAI
Current reasoning model
OpenAI GPT Terra 5.6 (max) ranks in this snapshot with Intelligence Index 42, 1M context, cost per task $1.40, median 102 tok/s, and first chunk 172.37s.
Best for: OpenAI coding agents, long-context work, and snapshot-based model comparison.
OpenAI
Current reasoning model
Z AI GLM 5.3 Flash ranks in this snapshot with Intelligence Index 42, 1M context, cost per task $0.25, median 53 tok/s, and first chunk 3.29s.
Best for: Z AI coding agents, long-context work, and snapshot-based model comparison.
Z AI
Current reasoning model
Google Gemini 3.8 Flash (high) ranks in this snapshot with Intelligence Index 41, 1M context, cost per task $1.24, median 242 tok/s, and first chunk 16.13s.
Best for: Google coding agents, long-context work, and snapshot-based model comparison.
Current reasoning model
Anthropic Claude Sonnet 5.5 (medium) ranks in this snapshot with Intelligence Index 41, 1M context, cost per task $0.59, median 107 tok/s, and first chunk 1.21s.
Best for: Anthropic coding agents, long-context work, and snapshot-based model comparison.
Anthropic
Current reasoning model
Alibaba Qwen 3.8 2.4T A95B ranks in this snapshot with Intelligence Index 40, 262k context, cost per task $2.16, median 39 tok/s, and first chunk 2.78s.
Best for: Alibaba coding agents, long-context work, and snapshot-based model comparison.
Alibaba
Current reasoning model
Alibaba Qwen 3.8 Flash Next ranks in this snapshot with Intelligence Index 40, 256k context, cost per task $0.37, median 54 tok/s, and first chunk 2.45s.
Best for: Alibaba coding agents, long-context work, and snapshot-based model comparison.
Alibaba
Current model; partial public metrics
Google Gemini 3.8 Flash (medium) ranks in this snapshot with Intelligence Index 40, 1M context, and cost per task $0.93. Output speed and latency are not published yet.
Best for: Google coding agents, long-context work, and snapshot-based model comparison.
Current reasoning model
DeepSeek DeepSeek V4.1 Flash (max) ranks in this snapshot with Intelligence Index 39, 1M context, cost per task $0.27, median 224 tok/s, and first chunk 1.02s.
Best for: DeepSeek coding agents, long-context work, and snapshot-based model comparison.
DeepSeek
Current reasoning model
OpenAI GPT Luna 6 (max) ranks in this snapshot with Intelligence Index 38, 1M context, cost per task $0.07, median 129 tok/s, and first chunk 132.77s.
Best for: OpenAI coding agents, long-context work, and snapshot-based model comparison.
OpenAI
Current reasoning model
OpenAI GPT Terra 5.6 (xhigh) ranks in this snapshot with Intelligence Index 38, 1M context, cost per task $0.63, median 91 tok/s, and first chunk 28.50s.
Best for: OpenAI coding agents, long-context work, and snapshot-based model comparison.
OpenAI
Current reasoning model
Xiaomi MiMo V2.6 Flash ranks in this snapshot with Intelligence Index 38, 1M context, cost per task $0.06, median 50 tok/s, and first chunk 4.75s.
Best for: Xiaomi coding agents, long-context work, and snapshot-based model comparison.
Xiaomi
Current reasoning model
DeepSeek DeepSeek V4 Pro 0813 (max) ranks in this snapshot with Intelligence Index 36, 1M context, cost per task $0.67, median 109 tok/s, and first chunk 1.73s.
Best for: DeepSeek coding agents, long-context work, and snapshot-based model comparison.
DeepSeek
Current reasoning model
Anthropic Claude Sonnet 5.5 (low) ranks in this snapshot with Intelligence Index 36, 1M context, cost per task $0.42, median 100 tok/s, and first chunk 1.35s.
Best for: Anthropic coding agents, long-context work, and snapshot-based model comparison.
Anthropic
Current reasoning model
DeepSeek DeepSeek V4 Flash Vision (max) ranks in this snapshot with Intelligence Index 35, 1M context, cost per task $0.31, median 219 tok/s, and first chunk 0.94s.
Best for: DeepSeek coding agents, long-context work, and snapshot-based model comparison.
DeepSeek
Current reasoning model
OpenAI GPT Luna 6 (xhigh) ranks in this snapshot with Intelligence Index 35, 1M context, cost per task $0.04, median 138 tok/s, and first chunk 20.86s.
Best for: OpenAI coding agents, long-context work, and snapshot-based model comparison.
OpenAI
Current reasoning model
Z AI GLM 5.3 (low) ranks in this snapshot with Intelligence Index 34, 1M context, cost per task $0.85, median 69 tok/s, and first chunk 3.13s.
Best for: Z AI coding agents, long-context work, and snapshot-based model comparison.
Z AI