Leaderboard
| # | The model name. | The company that makes the model. | Overall score. 50 is the middle. | Output tokens per second. | LMArena rating and rank. | Share of the index weight with results. | Maximum tokens in one request. | US dollars per 1M input tokens. | US dollars per 1M output tokens. | StateShows if the model has enough results for an index. | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 01 |  GPT-6 Astra | OpenAI | 83.5 ±2.8 | 28/s | 1444 (#59) | 95% | 1.05M | $10 | $50 | available | |
| 02 |  Claude Opus 5.5 | Anthropic | 82.8 ±3.6 | 85/s | — | 95% | 1M | $4 | $20 | available | |
| 03 | Claude Fable 5.1 | Anthropic | 81.4 ±2.7 | 49/s | 1508 (#1) | 95% | 1M | $10 | $50 | available | |
| 04 | Claude Opus 5 | Anthropic | 77.9 ±2.5 | 54/s | 1505 (#3) | 95% | 1M | $5 | $25 | available | |
| 05 | Claude Fable 5 | Anthropic | 77.5 ±2.7 | 34/s | 1493 (#7) | 95% | 1M | $10 | $50 | available | |
| 06 | GPT-5.6 Sol | OpenAI | 76.7 ±2.1 | 38/s | 1455 (#37) | 100% | 1.05M | $2 | $10 | available | |
| 07 | GPT-5.6 Terra | OpenAI | 73.4 ±2.3 | 36/s | 1446 (#52) | 100% | 1.05M | $2 | $12 | available | |
| 08 | GPT-6 Sol | OpenAI | 76.9 ±6.0 | — | — | 80% | 1.05M | $2 | $10 | available | |
| 09 |  Muse Spark 1.3 | Meta | 75.0 ±4.2 | 66/s | 1490 (#10) | 85% | 1.05M | $1.25 | $4.25 | available | |
| 10 |  Gemini 3.7 Flash | 72.3 ±2.3 | 80/s | 1490 (#8) | 100% | 1.05M | $0.75 | $3.75 | available | ||
| 11 | GPT-5.5 | OpenAI | 72.3 ±2.6 | 53/s | 1466 (#31) | 95% | 1.05M | $5 | $30 | available | |
| 12 | Gemini 3.8 Flash | 72.1 ±2.9 | 86/s | 1495 (#6) | 95% | 1.05M | $0.75 | $3.75 | available | ||
| 13 | GPT-5.5 Pro | OpenAI | 77.9 ±8.7 | 5/s | — | 60% | 1.05M | $30 | $180 | available | |
| 14 | Claude Opus 4.8 | Anthropic | 71.1 ±2.6 | 58/s | 1453 (#40) | 95% | 1M | $5 | $25 | available | |
| 15 |  Grok 4.6 | xAI | 71.8 ±3.8 | 52/s | 1430 (#87) | 85% | 500K | $2 | $6 | available | |
| 16 | GPT-5.4 Pro | OpenAI | 76.5 ±8.7 | 1/s | — | 60% | 1.05M | $30 | $180 | available | |
| 17 | MAKimi K3 | Moonshot AI | 72.0 ±4.6 | 37/s | — | 80% | 1.05M | $3 | $15 | available | |
| 18 | STStep 5 Preview | StepFun | 72.5 ±5.3 | 83/s | — | 80% | 1M | $1 | $2.7 | available | |
| 19 | GPT-5.6 Luna | OpenAI | 69.9 ±2.7 | 58/s | 1430 (#86) | 95% | 1.05M | $0.2 | $1.2 | available | |
| 20 |  MiMo-V2.6-Pro | Xiaomi | 73.5 ±6.7 | 38/s | — | 70% | 1.05M | $0.435 | $0.87 | available | |
| 21 |  DeepSeek V4.1 Flash | DeepSeek | 70.6 ±4.0 | 103/s | — | 90% | 1.05M | $0.15 | $0.6 | available | |
| 22 | TEHy4 preview | Tencent | 70.2 ±4.3 | 40/s | — | 90% | 1.05M | $0.834 | $2.5 | available | |
| 23 |  GLM-5.3 | Z.AI | 69.6 ±3.8 | 152/s | 1475 (#20) | 85% | 1.31M | $0.84 | $2.64 | available | |
| 24 | Muse Spark 1.2 | Meta | 69.2 ±3.4 | 126/s | 1489 (#11) | 95% | 1.05M | $1.25 | $4.25 | available | |
| 25 |  Qwen3.8 Max | Alibaba | 68.4 ±2.8 | 39/s | — | 95% | 1M | N/A | N/A | available | |
| 26 | Grok 4.7 | xAI | 70.1 ±4.8 | 51/s | — | 85% | 500K | $1.6 | $4.8 | available | |
| 27 | GPT-5.4 | OpenAI | 67.6 ±2.6 | 32/s | 1453 (#41) | 95% | 1.05M | $2.5 | $15 | available | |
| 28 | Claude Sonnet 5 | Anthropic | 67.6 ±2.8 | 44/s | 1442 (#62) | 95% | 1M | $2 | $10 | available | |
| 29 | Gemini 3.5 Flash | 67.3 ±2.7 | 132/s | 1482 (#13) | 95% | 1.05M | $1.5 | $9 | available | ||
| 30 | DeepSeek V4 Pro 0813 | DeepSeek | 68.8 ±4.4 | 68/s | — | 85% | 1M | $0.435 | $0.87 | available | |
| 31 | Gemini 3.6 Flash | 66.8 ±2.5 | 133/s | 1476 (#18) | 100% | 1.05M | $0.75 | $3.75 | available | ||
| 32 | Muse Spark 1.1 | Meta | 67.0 ±3.1 | 217/s | 1480 (#15) | 95% | 1.05M | $1.25 | $4.25 | available | |
| 33 | GLM-5.3-Flash | Z.AI | 65.6 ±2.5 | 69/s | 1472 (#24) | 100% | 1.31M | $0.15 | $0.5 | available | |
| 34 | Qwen3.8-Flash-Next | Alibaba | 66.4 ±3.4 | 54/s | — | 95% | 262K | Free | Free | available | |
| 35 | Grok 4.5 | xAI | 66.0 ±3.0 | 49/s | 1450 (#45) | 95% | 500K | $2 | $6 | available | |
| 36 | Claude Mythos 5 | Anthropic | 72.0 ±9.2 | — | — | 65% | 1M | $10 | $50 | available | |
| 37 | Qwen3.8 Max Preview | Alibaba | 69.0 ±6.7 | — | — | 80% | N/A | N/A | N/A | available | |
| 38 | GPT-6 Luna | OpenAI | 68.4 ±6.7 | — | — | 80% | 1.05M | $0.1 | $0.5 | available | |
| 39 | Gemini 3.1 Pro | 64.7 ±3.2 | 115/s | — | 95% | 1M | $2 | $12 | available | ||
| 40 | Claude Opus 4.7 (Adaptive) | Anthropic | 66.2 ±4.8 | — | — | 85% | 1M | $5 | $25 | available | |
| 41 | Qwen3.8-27B | Alibaba | 63.1 ±2.4 | 44/s | 1439 (#68) | 100% | 1M | $0.42 | $3 | available | |
| 42 | Claude Opus 4.7 | Anthropic | 63.3 ±3.0 | 43/s | 1483 (#12) | 95% | 1M | $5 | $25 | available | |
| 43 | DSdots3-note Preview | Dots Studio | 65.5 ±5.3 | — | — | 85% | 512K | Free | Free | available | |
| 44 | GPT-5.2 | OpenAI | 62.2 ±2.4 | 43/s | 1412 (#125) | 100% | 400K | $1.75 | $14 | available | |
| 45 | GPT-5.3 Codex | OpenAI | 64.8 ±5.2 | 80/s | — | 85% | 400K | $1.75 | $14 | available | |
| 46 | DeepSeek V4 Flash 0731 | DeepSeek | 64.6 ±5.0 | 221/s | — | 80% | 1M | $0.14 | $0.28 | available | |
| 47 | Qwen3.7 Max | Alibaba | 62.6 ±3.8 | 61/s | — | 85% | 1M | $1.48 | $4.43 | available | |
| 48 | GLM-5.2 | Z.AI | 62.7 ±3.8 | 74/s | 1467 (#29) | 85% | 1.05M | $0.65 | $2.04 | available | |
| 49 | Muse Spark | Meta | 61.6 ±3.4 | — | 1473 (#22) | 95% | 262K | N/A | N/A | available | |
| 50 | GPT-5.2-Codex | OpenAI | 62.1 ±4.1 | 15/s | — | 95% | 400K | $1.75 | $14 | available |
01GPT-6 AstraOpenAI83.5 ±2.8
- SpeedOutput tokens per second.
- 28/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1444 (#59)
- InputUS dollars per 1M input tokens.
- $10
- OutputUS dollars per 1M output tokens.
- $50
02Claude Opus 5.5Anthropic82.8 ±3.6
- SpeedOutput tokens per second.
- 85/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $4
- OutputUS dollars per 1M output tokens.
- $20
03Claude Fable 5.1Anthropic81.4 ±2.7
- SpeedOutput tokens per second.
- 49/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- 1508 (#1)
- InputUS dollars per 1M input tokens.
- $10
- OutputUS dollars per 1M output tokens.
- $50
04Claude Opus 5Anthropic77.9 ±2.5
- SpeedOutput tokens per second.
- 54/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- 1505 (#3)
- InputUS dollars per 1M input tokens.
- $5
- OutputUS dollars per 1M output tokens.
- $25
05Claude Fable 5Anthropic77.5 ±2.7
- SpeedOutput tokens per second.
- 34/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- 1493 (#7)
- InputUS dollars per 1M input tokens.
- $10
- OutputUS dollars per 1M output tokens.
- $50
06GPT-5.6 SolOpenAI76.7 ±2.1
- SpeedOutput tokens per second.
- 38/s
- CoverageShare of the index weight with results.
- 100%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1455 (#37)
- InputUS dollars per 1M input tokens.
- $2
- OutputUS dollars per 1M output tokens.
- $10
07GPT-5.6 TerraOpenAI73.4 ±2.3
- SpeedOutput tokens per second.
- 36/s
- CoverageShare of the index weight with results.
- 100%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1446 (#52)
- InputUS dollars per 1M input tokens.
- $2
- OutputUS dollars per 1M output tokens.
- $12
08GPT-6 SolOpenAI76.9 ±6.0
- SpeedOutput tokens per second.
- —
- CoverageShare of the index weight with results.
- 80%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $2
- OutputUS dollars per 1M output tokens.
- $10
09Muse Spark 1.3Meta75.0 ±4.2
- SpeedOutput tokens per second.
- 66/s
- CoverageShare of the index weight with results.
- 85%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1490 (#10)
- InputUS dollars per 1M input tokens.
- $1.25
- OutputUS dollars per 1M output tokens.
- $4.25
10Gemini 3.7 FlashGoogle72.3 ±2.3
- SpeedOutput tokens per second.
- 80/s
- CoverageShare of the index weight with results.
- 100%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1490 (#8)
- InputUS dollars per 1M input tokens.
- $0.75
- OutputUS dollars per 1M output tokens.
- $3.75
11GPT-5.5OpenAI72.3 ±2.6
- SpeedOutput tokens per second.
- 53/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1466 (#31)
- InputUS dollars per 1M input tokens.
- $5
- OutputUS dollars per 1M output tokens.
- $30
12Gemini 3.8 FlashGoogle72.1 ±2.9
- SpeedOutput tokens per second.
- 86/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1495 (#6)
- InputUS dollars per 1M input tokens.
- $0.75
- OutputUS dollars per 1M output tokens.
- $3.75
13GPT-5.5 ProOpenAI77.9 ±8.7
- SpeedOutput tokens per second.
- 5/s
- CoverageShare of the index weight with results.
- 60%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $30
- OutputUS dollars per 1M output tokens.
- $180
14Claude Opus 4.8Anthropic71.1 ±2.6
- SpeedOutput tokens per second.
- 58/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- 1453 (#40)
- InputUS dollars per 1M input tokens.
- $5
- OutputUS dollars per 1M output tokens.
- $25
15Grok 4.6xAI71.8 ±3.8
- SpeedOutput tokens per second.
- 52/s
- CoverageShare of the index weight with results.
- 85%
- ContextMaximum tokens in one request.
- 500K
- EloLMArena rating and rank.
- 1430 (#87)
- InputUS dollars per 1M input tokens.
- $2
- OutputUS dollars per 1M output tokens.
- $6
16GPT-5.4 ProOpenAI76.5 ±8.7
- SpeedOutput tokens per second.
- 1/s
- CoverageShare of the index weight with results.
- 60%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $30
- OutputUS dollars per 1M output tokens.
- $180
17MAKimi K3Moonshot AI72.0 ±4.6
- SpeedOutput tokens per second.
- 37/s
- CoverageShare of the index weight with results.
- 80%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $3
- OutputUS dollars per 1M output tokens.
- $15
18STStep 5 PreviewStepFun72.5 ±5.3
- SpeedOutput tokens per second.
- 83/s
- CoverageShare of the index weight with results.
- 80%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $1
- OutputUS dollars per 1M output tokens.
- $2.7
19GPT-5.6 LunaOpenAI69.9 ±2.7
- SpeedOutput tokens per second.
- 58/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1430 (#86)
- InputUS dollars per 1M input tokens.
- $0.2
- OutputUS dollars per 1M output tokens.
- $1.2
20MiMo-V2.6-ProXiaomi73.5 ±6.7
- SpeedOutput tokens per second.
- 38/s
- CoverageShare of the index weight with results.
- 70%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $0.435
- OutputUS dollars per 1M output tokens.
- $0.87
21DeepSeek V4.1 FlashDeepSeek70.6 ±4.0
- SpeedOutput tokens per second.
- 103/s
- CoverageShare of the index weight with results.
- 90%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $0.15
- OutputUS dollars per 1M output tokens.
- $0.6
22TEHy4 previewTencent70.2 ±4.3
- SpeedOutput tokens per second.
- 40/s
- CoverageShare of the index weight with results.
- 90%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $0.834
- OutputUS dollars per 1M output tokens.
- $2.5
23GLM-5.3Z.AI69.6 ±3.8
- SpeedOutput tokens per second.
- 152/s
- CoverageShare of the index weight with results.
- 85%
- ContextMaximum tokens in one request.
- 1.31M
- EloLMArena rating and rank.
- 1475 (#20)
- InputUS dollars per 1M input tokens.
- $0.84
- OutputUS dollars per 1M output tokens.
- $2.64
24Muse Spark 1.2Meta69.2 ±3.4
- SpeedOutput tokens per second.
- 126/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1489 (#11)
- InputUS dollars per 1M input tokens.
- $1.25
- OutputUS dollars per 1M output tokens.
- $4.25
25Qwen3.8 MaxAlibaba68.4 ±2.8
- SpeedOutput tokens per second.
- 39/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- N/A
- OutputUS dollars per 1M output tokens.
- N/A
26Grok 4.7xAI70.1 ±4.8
- SpeedOutput tokens per second.
- 51/s
- CoverageShare of the index weight with results.
- 85%
- ContextMaximum tokens in one request.
- 500K
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $1.6
- OutputUS dollars per 1M output tokens.
- $4.8
27GPT-5.4OpenAI67.6 ±2.6
- SpeedOutput tokens per second.
- 32/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1453 (#41)
- InputUS dollars per 1M input tokens.
- $2.5
- OutputUS dollars per 1M output tokens.
- $15
28Claude Sonnet 5Anthropic67.6 ±2.8
- SpeedOutput tokens per second.
- 44/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- 1442 (#62)
- InputUS dollars per 1M input tokens.
- $2
- OutputUS dollars per 1M output tokens.
- $10
29Gemini 3.5 FlashGoogle67.3 ±2.7
- SpeedOutput tokens per second.
- 132/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1482 (#13)
- InputUS dollars per 1M input tokens.
- $1.5
- OutputUS dollars per 1M output tokens.
- $9
30DeepSeek V4 Pro 0813DeepSeek68.8 ±4.4
- SpeedOutput tokens per second.
- 68/s
- CoverageShare of the index weight with results.
- 85%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $0.435
- OutputUS dollars per 1M output tokens.
- $0.87
31Gemini 3.6 FlashGoogle66.8 ±2.5
- SpeedOutput tokens per second.
- 133/s
- CoverageShare of the index weight with results.
- 100%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1476 (#18)
- InputUS dollars per 1M input tokens.
- $0.75
- OutputUS dollars per 1M output tokens.
- $3.75
32Muse Spark 1.1Meta67.0 ±3.1
- SpeedOutput tokens per second.
- 217/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1480 (#15)
- InputUS dollars per 1M input tokens.
- $1.25
- OutputUS dollars per 1M output tokens.
- $4.25
33GLM-5.3-FlashZ.AI65.6 ±2.5
- SpeedOutput tokens per second.
- 69/s
- CoverageShare of the index weight with results.
- 100%
- ContextMaximum tokens in one request.
- 1.31M
- EloLMArena rating and rank.
- 1472 (#24)
- InputUS dollars per 1M input tokens.
- $0.15
- OutputUS dollars per 1M output tokens.
- $0.5
34Qwen3.8-Flash-NextAlibaba66.4 ±3.4
- SpeedOutput tokens per second.
- 54/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 262K
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- Free
- OutputUS dollars per 1M output tokens.
- Free
35Grok 4.5xAI66.0 ±3.0
- SpeedOutput tokens per second.
- 49/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 500K
- EloLMArena rating and rank.
- 1450 (#45)
- InputUS dollars per 1M input tokens.
- $2
- OutputUS dollars per 1M output tokens.
- $6
36Claude Mythos 5Anthropic72.0 ±9.2
- SpeedOutput tokens per second.
- —
- CoverageShare of the index weight with results.
- 65%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $10
- OutputUS dollars per 1M output tokens.
- $50
37Qwen3.8 Max PreviewAlibaba69.0 ±6.7
- SpeedOutput tokens per second.
- —
- CoverageShare of the index weight with results.
- 80%
- ContextMaximum tokens in one request.
- N/A
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- N/A
- OutputUS dollars per 1M output tokens.
- N/A
38GPT-6 LunaOpenAI68.4 ±6.7
- SpeedOutput tokens per second.
- —
- CoverageShare of the index weight with results.
- 80%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $0.1
- OutputUS dollars per 1M output tokens.
- $0.5
39Gemini 3.1 ProGoogle64.7 ±3.2
- SpeedOutput tokens per second.
- 115/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $2
- OutputUS dollars per 1M output tokens.
- $12
40Claude Opus 4.7 (Adaptive)Anthropic66.2 ±4.8
- SpeedOutput tokens per second.
- —
- CoverageShare of the index weight with results.
- 85%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $5
- OutputUS dollars per 1M output tokens.
- $25
41Qwen3.8-27BAlibaba63.1 ±2.4
- SpeedOutput tokens per second.
- 44/s
- CoverageShare of the index weight with results.
- 100%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- 1439 (#68)
- InputUS dollars per 1M input tokens.
- $0.42
- OutputUS dollars per 1M output tokens.
- $3
42Claude Opus 4.7Anthropic63.3 ±3.0
- SpeedOutput tokens per second.
- 43/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- 1483 (#12)
- InputUS dollars per 1M input tokens.
- $5
- OutputUS dollars per 1M output tokens.
- $25
43DSdots3-note PreviewDots Studio65.5 ±5.3
- SpeedOutput tokens per second.
- —
- CoverageShare of the index weight with results.
- 85%
- ContextMaximum tokens in one request.
- 512K
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- Free
- OutputUS dollars per 1M output tokens.
- Free
44GPT-5.2OpenAI62.2 ±2.4
- SpeedOutput tokens per second.
- 43/s
- CoverageShare of the index weight with results.
- 100%
- ContextMaximum tokens in one request.
- 400K
- EloLMArena rating and rank.
- 1412 (#125)
- InputUS dollars per 1M input tokens.
- $1.75
- OutputUS dollars per 1M output tokens.
- $14
45GPT-5.3 CodexOpenAI64.8 ±5.2
- SpeedOutput tokens per second.
- 80/s
- CoverageShare of the index weight with results.
- 85%
- ContextMaximum tokens in one request.
- 400K
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $1.75
- OutputUS dollars per 1M output tokens.
- $14
46DeepSeek V4 Flash 0731DeepSeek64.6 ±5.0
- SpeedOutput tokens per second.
- 221/s
- CoverageShare of the index weight with results.
- 80%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $0.14
- OutputUS dollars per 1M output tokens.
- $0.28
47Qwen3.7 MaxAlibaba62.6 ±3.8
- SpeedOutput tokens per second.
- 61/s
- CoverageShare of the index weight with results.
- 85%
- ContextMaximum tokens in one request.
- 1M
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $1.48
- OutputUS dollars per 1M output tokens.
- $4.43
48GLM-5.2Z.AI62.7 ±3.8
- SpeedOutput tokens per second.
- 74/s
- CoverageShare of the index weight with results.
- 85%
- ContextMaximum tokens in one request.
- 1.05M
- EloLMArena rating and rank.
- 1467 (#29)
- InputUS dollars per 1M input tokens.
- $0.65
- OutputUS dollars per 1M output tokens.
- $2.04
49Muse SparkMeta61.6 ±3.4
- SpeedOutput tokens per second.
- —
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 262K
- EloLMArena rating and rank.
- 1473 (#22)
- InputUS dollars per 1M input tokens.
- N/A
- OutputUS dollars per 1M output tokens.
- N/A
50GPT-5.2-CodexOpenAI62.1 ±4.1
- SpeedOutput tokens per second.
- 15/s
- CoverageShare of the index weight with results.
- 95%
- ContextMaximum tokens in one request.
- 400K
- EloLMArena rating and rank.
- —
- InputUS dollars per 1M input tokens.
- $1.75
- OutputUS dollars per 1M output tokens.
- $14