Leaderboards
One board per question
No single ranking answers every question. Pick the measurement that matches the work you are actually doing — a model that tops GPQA may be nowhere near the top on long-context retrieval.
Headline
The composite indices
Aggregate scores. Useful for a shortlist, misleading as a final answer.
Intelligence Index
index · higher is better
- Qwen3.8 MaxQwen58.1
- Claude Opus 5.5Anthropic57.6
- Claude Sonnet 5.5Anthropic56.0
- Claude Fable 5.1Anthropic53.4
- GPT-6 AstraOpenAI52.7
- Gemini 4 ArgonGoogle52.6
- Muse WonderMeta52.4
- GPT-6.1 SolOpenAI51.8
- Claude Opus 5Anthropic50.8
- Claude Fable 5Anthropic49.6
Composite of ten reasoning, knowledge, coding and agentic evaluations.
View as table
| Model | index |
|---|---|
| Qwen3.8 Max (Qwen) | 58.1 |
| Claude Opus 5.5 (Anthropic) | 57.6 |
| Claude Sonnet 5.5 (Anthropic) | 56.0 |
| Claude Fable 5.1 (Anthropic) | 53.4 |
| GPT-6 Astra (OpenAI) | 52.7 |
| Gemini 4 Argon (Google) | 52.6 |
| Muse Wonder (Meta) | 52.4 |
| GPT-6.1 Sol (OpenAI) | 51.8 |
| Claude Opus 5 (Anthropic) | 50.8 |
| Claude Fable 5 (Anthropic) | 49.6 |
Coding Index
index · higher is better
- Claude Fable 5.1Anthropic81.6
- Claude Opus 5Anthropic78.0
- GPT-5.6 SolOpenAI77.4
- GPT-6 AstraOpenAI76.9
- Grok 4.6xAI76.8
- GPT-5.6 TerraOpenAI76.7
- Claude Fable 5Anthropic76.5
- Gemini 3.8 FlashGoogle76.3
- 76.2
- Kimi K3Moonshot AI76.2
SciCode, LiveCodeBench and Terminal-Bench Hard, combined.
View as table
| Model | index |
|---|---|
| Claude Fable 5.1 (Anthropic) | 81.6 |
| Claude Opus 5 (Anthropic) | 78.0 |
| GPT-5.6 Sol (OpenAI) | 77.4 |
| GPT-6 Astra (OpenAI) | 76.9 |
| Grok 4.6 (xAI) | 76.8 |
| GPT-5.6 Terra (OpenAI) | 76.7 |
| Claude Fable 5 (Anthropic) | 76.5 |
| Gemini 3.8 Flash (Google) | 76.3 |
| Qwen3.8 Max (0902) (Qwen) | 76.2 |
| Kimi K3 (Moonshot AI) | 76.2 |
Agentic Index
index · higher is better
- Qwen3.8 MaxQwen58.4
- Claude Fable 5.1Anthropic57.9
- Claude Opus 5Anthropic56.5
- 56.0
- Muse Spark 1.3Meta55.5
- GLM 5.3Z.ai53.1
- Grok 4.6xAI53.0
- GPT-6 AstraOpenAI51.0
- GLM 5.3 FlashZ.ai50.9
- Claude Fable 5Anthropic50.7
Tool use, long-horizon planning and terminal work.
View as table
| Model | index |
|---|---|
| Qwen3.8 Max (Qwen) | 58.4 |
| Claude Fable 5.1 (Anthropic) | 57.9 |
| Claude Opus 5 (Anthropic) | 56.5 |
| Qwen3.8 Max (0902) (Qwen) | 56.0 |
| Muse Spark 1.3 (Meta) | 55.5 |
| GLM 5.3 (Z.ai) | 53.1 |
| Grok 4.6 (xAI) | 53.0 |
| GPT-6 Astra (OpenAI) | 51.0 |
| GLM 5.3 Flash (Z.ai) | 50.9 |
| Claude Fable 5 (Anthropic) | 50.7 |
Output speed
tokens/s · higher is better
- Apply 3Relace6,866 t/s
- V3 LargeMorph3,208 t/s
- V3 FastMorph3,005 t/s
- gpt-oss-120bOpenAI641 t/s
- gpt-oss-safeguard-20bOpenAI537 t/s
- 461 t/s
- gpt-oss-20bOpenAI410 t/s
- Qwen3.8 27BQwen409 t/s
- 406 t/s
- GLM 5.2Z.ai368 t/s
Median output tokens per second across serving providers.
View as table
| Model | tokens/s |
|---|---|
| Apply 3 (Relace) | 6,866 t/s |
| V3 Large (Morph) | 3,208 t/s |
| V3 Fast (Morph) | 3,005 t/s |
| gpt-oss-120b (OpenAI) | 641 t/s |
| gpt-oss-safeguard-20b (OpenAI) | 537 t/s |
| Llama 3.1 8B Instruct (Meta) | 461 t/s |
| gpt-oss-20b (OpenAI) | 410 t/s |
| Qwen3.8 27B (Qwen) | 409 t/s |
| Grok 4.20 Multi-Agent (xAI) | 406 t/s |
| GLM 5.2 (Z.ai) | 368 t/s |
Context window
tokens · higher is better
- 2M
- Grok 4.20xAI2M
- Llama 4 ScoutMeta1.31M
- GPT-6.1 Sol ProOpenAI1.05M
- GPT-6.1 SolOpenAI1.05M
- GPT-6 Luna ProOpenAI1.05M
- GPT-6 LunaOpenAI1.05M
- GPT-6 Sol ProOpenAI1.05M
- GPT-6 SolOpenAI1.05M
- MiMo-V2.6-FlashXiaomi1.05M
Maximum tokens the model accepts in one request.
View as table
| Model | tokens |
|---|---|
| Grok 4.20 Multi-Agent (xAI) | 2M |
| Grok 4.20 (xAI) | 2M |
| Llama 4 Scout (Meta) | 1.31M |
| GPT-6.1 Sol Pro (OpenAI) | 1.05M |
| GPT-6.1 Sol (OpenAI) | 1.05M |
| GPT-6 Luna Pro (OpenAI) | 1.05M |
| GPT-6 Luna (OpenAI) | 1.05M |
| GPT-6 Sol Pro (OpenAI) | 1.05M |
| GPT-6 Sol (OpenAI) | 1.05M |
| MiMo-V2.6-Flash (Xiaomi) | 1.05M |
Arena Elo
Dot position on a 1,350–1,500 scale
- Claude Opus 5.5Anthropic1,479
- Claude Sonnet 5.5Anthropic1,468
- GPT-6 AstraOpenAI1,468
- GPT-6.1 SolOpenAI1,464
- Claude Fable 5.1Anthropic1,393
- Kimi K3Moonshot AI1,388
- Gemini 4 ArgonGoogle1,387
- GPT-5.6 SolOpenAI1,385
- Muse Spark 1.3Meta1,360
- V4.1 FlashDeepSeek1,357
1,3501,500
Head-to-head generation quality, judged pairwise. Elo has no meaningful zero, so bars from a zero baseline would flatten every gap.
View as table
| Model | Elo |
|---|---|
| Claude Opus 5.5 (Anthropic) | 1,479 |
| Claude Sonnet 5.5 (Anthropic) | 1,468 |
| GPT-6 Astra (OpenAI) | 1,468 |
| GPT-6.1 Sol (OpenAI) | 1,464 |
| Claude Fable 5.1 (Anthropic) | 1,393 |
| Kimi K3 (Moonshot AI) | 1,388 |
| Gemini 4 Argon (Google) | 1,387 |
| GPT-5.6 Sol (OpenAI) | 1,385 |
| Muse Spark 1.3 (Meta) | 1,360 |
| V4.1 Flash (DeepSeek) | 1,357 |
Individual evaluations
The measurements underneath
Each of these is a real test with its own failure modes. A model absent from a board was not run on it — that is not the same as scoring zero.
GPQA Diamond
Percentage correct · higher is better
- GPT-6 AstraOpenAI96.1%
- Gemini 3.8 FlashGoogle95.3%
- Grok 4.6xAI94.9%
- Gemini 3.7 FlashGoogle94.5%
- GPT-5.6 SolOpenAI94.1%
- Gemini 3.1 Pro PreviewGoogle94.1%
- Claude Fable 5.1Anthropic93.7%
- Muse Spark 1.3Meta93.5%
- 93.5%
- Kimi K3Moonshot AI93.5%
Graduate-level science questions written to resist search.
View as table
| Model | Score |
|---|---|
| GPT-6 Astra (OpenAI) | 96.1% |
| Gemini 3.8 Flash (Google) | 95.3% |
| Grok 4.6 (xAI) | 94.9% |
| Gemini 3.7 Flash (Google) | 94.5% |
| GPT-5.6 Sol (OpenAI) | 94.1% |
| Gemini 3.1 Pro Preview (Google) | 94.1% |
| Claude Fable 5.1 (Anthropic) | 93.7% |
| Muse Spark 1.3 (Meta) | 93.5% |
| Qwen3.8 2.4T A95B (Qwen) | 93.5% |
| Kimi K3 (Moonshot AI) | 93.5% |
Humanity's Last Exam
Percentage correct · higher is better
- Claude Opus 5.5Anthropic61.4%
- Claude Fable 5.1Anthropic59.1%
- Gemini 4 ArgonGoogle57.1%
- Claude Fable 5Anthropic55.5%
- Claude Sonnet 5.5Anthropic55.0%
- Claude Opus 5Anthropic54.9%
- GPT-6 AstraOpenAI54.7%
- GPT-6.1 SolOpenAI52.9%
- Muse WonderMeta50.1%
- GPT-5.6 SolOpenAI49.5%
A deliberately brutal cross-disciplinary exam; scores stay low.
View as table
| Model | Score |
|---|---|
| Claude Opus 5.5 (Anthropic) | 61.4% |
| Claude Fable 5.1 (Anthropic) | 59.1% |
| Gemini 4 Argon (Google) | 57.1% |
| Claude Fable 5 (Anthropic) | 55.5% |
| Claude Sonnet 5.5 (Anthropic) | 55.0% |
| Claude Opus 5 (Anthropic) | 54.9% |
| GPT-6 Astra (OpenAI) | 54.7% |
| GPT-6.1 Sol (OpenAI) | 52.9% |
| Muse Wonder (Meta) | 50.1% |
| GPT-5.6 Sol (OpenAI) | 49.5% |
SciCode
Percentage correct · higher is better
- Claude Opus 5.5Anthropic66.9%
- Claude Fable 5.1Anthropic63.1%
- Gemini 4 ArgonGoogle61.8%
- Claude Sonnet 5.5Anthropic61.0%
- Claude Fable 5Anthropic61.0%
- MiMo-V2.6-ProXiaomi60.9%
- Muse WonderMeta60.3%
- Kimi K3Moonshot AI59.5%
- GLM 5.3Z.ai59.0%
- Step 5 PreviewStepFun58.9%
Research-grade scientific coding problems.
View as table
| Model | Score |
|---|---|
| Claude Opus 5.5 (Anthropic) | 66.9% |
| Claude Fable 5.1 (Anthropic) | 63.1% |
| Gemini 4 Argon (Google) | 61.8% |
| Claude Sonnet 5.5 (Anthropic) | 61.0% |
| Claude Fable 5 (Anthropic) | 61.0% |
| MiMo-V2.6-Pro (Xiaomi) | 60.9% |
| Muse Wonder (Meta) | 60.3% |
| Kimi K3 (Moonshot AI) | 59.5% |
| GLM 5.3 (Z.ai) | 59.0% |
| Step 5 Preview (StepFun) | 58.9% |
τ²-bench (Telecom)
Percentage correct · higher is better
- GLM 5.2Z.ai99.1%
- GLM 4.7 FlashZ.ai98.8%
- Claude Fable 5Anthropic98.5%
- Step 3.7 FlashStepFun98.5%
- GLM 5V TurboZ.ai98.5%
- GLM 5 TurboZ.ai98.5%
- GLM 5Z.ai98.2%
- Grok 4.3xAI97.7%
- GLM 5.1Z.ai97.7%
- Qwen3.6 PlusQwen97.7%
Tool-use and policy adherence in a simulated telecom support agent.
View as table
| Model | Score |
|---|---|
| GLM 5.2 (Z.ai) | 99.1% |
| GLM 4.7 Flash (Z.ai) | 98.8% |
| Claude Fable 5 (Anthropic) | 98.5% |
| Step 3.7 Flash (StepFun) | 98.5% |
| GLM 5V Turbo (Z.ai) | 98.5% |
| GLM 5 Turbo (Z.ai) | 98.5% |
| GLM 5 (Z.ai) | 98.2% |
| Grok 4.3 (xAI) | 97.7% |
| GLM 5.1 (Z.ai) | 97.7% |
| Qwen3.6 Plus (Qwen) | 97.7% |
Terminal-Bench Hard
Percentage correct · higher is better
- GPT-5.6 SolOpenAI65.9%
- Claude Fable 5Anthropic62.9%
- GPT-5.5OpenAI60.6%
- Claude Opus 4.8Anthropic58.3%
- GPT-5.6 TerraOpenAI57.6%
- GPT-5.4OpenAI57.6%
- Gemini 3.1 Pro PreviewGoogle53.8%
- GPT-5.3-CodexOpenAI53.0%
- GPT-5.4 MiniOpenAI52.3%
- Claude Opus 4.7Anthropic51.5%
Hard end-to-end tasks solved inside a real terminal.
View as table
| Model | Score |
|---|---|
| GPT-5.6 Sol (OpenAI) | 65.9% |
| Claude Fable 5 (Anthropic) | 62.9% |
| GPT-5.5 (OpenAI) | 60.6% |
| Claude Opus 4.8 (Anthropic) | 58.3% |
| GPT-5.6 Terra (OpenAI) | 57.6% |
| GPT-5.4 (OpenAI) | 57.6% |
| Gemini 3.1 Pro Preview (Google) | 53.8% |
| GPT-5.3-Codex (OpenAI) | 53.0% |
| GPT-5.4 Mini (OpenAI) | 52.3% |
| Claude Opus 4.7 (Anthropic) | 51.5% |
LiveCodeBench
Percentage correct · higher is better
- GLM 4.7Z.ai89.4%
- GPT-5.2OpenAI88.9%
- gpt-oss-120bOpenAI87.8%
- GPT-5.1OpenAI86.8%
- o4 Mini HighOpenAI85.9%
- o4 MiniOpenAI85.9%
- Kimi K2 ThinkingMoonshot AI85.3%
- GPT-5.1-CodexOpenAI84.9%
- GPT-5OpenAI84.6%
- GPT-5 MiniOpenAI83.8%
Contest programming on problems released after training.
View as table
| Model | Score |
|---|---|
| GLM 4.7 (Z.ai) | 89.4% |
| GPT-5.2 (OpenAI) | 88.9% |
| gpt-oss-120b (OpenAI) | 87.8% |
| GPT-5.1 (OpenAI) | 86.8% |
| o4 Mini High (OpenAI) | 85.9% |
| o4 Mini (OpenAI) | 85.9% |
| Kimi K2 Thinking (Moonshot AI) | 85.3% |
| GPT-5.1-Codex (OpenAI) | 84.9% |
| GPT-5 (OpenAI) | 84.6% |
| GPT-5 Mini (OpenAI) | 83.8% |
AA-LCR (long context)
Percentage correct · higher is better
- Kimi K3Moonshot AI88.7%
- Step 5 PreviewStepFun88.3%
- MiMo-V2.6-ProXiaomi86.3%
- Claude Fable 5.1Anthropic85.3%
- Claude Opus 5.5Anthropic84.7%
- GPT-5.5OpenAI84.3%
- V4.1 FlashDeepSeek84.0%
- GPT-5.6 SolOpenAI84.0%
- GPT-6 SolOpenAI83.7%
- GPT-5.6 LunaOpenAI83.7%
Long-context reasoning across large documents.
View as table
| Model | Score |
|---|---|
| Kimi K3 (Moonshot AI) | 88.7% |
| Step 5 Preview (StepFun) | 88.3% |
| MiMo-V2.6-Pro (Xiaomi) | 86.3% |
| Claude Fable 5.1 (Anthropic) | 85.3% |
| Claude Opus 5.5 (Anthropic) | 84.7% |
| GPT-5.5 (OpenAI) | 84.3% |
| V4.1 Flash (DeepSeek) | 84.0% |
| GPT-5.6 Sol (OpenAI) | 84.0% |
| GPT-6 Sol (OpenAI) | 83.7% |
| GPT-5.6 Luna (OpenAI) | 83.7% |
AIME 2025
Percentage correct · higher is better
- GPT-5.2OpenAI99.0%
- GPT-5.1-CodexOpenAI95.7%
- GLM 4.7Z.ai95.0%
- Kimi K2 ThinkingMoonshot AI94.7%
- GPT-5OpenAI94.3%
- GPT-5.1OpenAI94.0%
- gpt-oss-120bOpenAI93.4%
- GPT-5.1-Codex-MiniOpenAI91.7%
- GPT-5 MiniOpenAI90.7%
- o4 Mini HighOpenAI90.7%
Competition mathematics.
View as table
| Model | Score |
|---|---|
| GPT-5.2 (OpenAI) | 99.0% |
| GPT-5.1-Codex (OpenAI) | 95.7% |
| GLM 4.7 (Z.ai) | 95.0% |
| Kimi K2 Thinking (Moonshot AI) | 94.7% |
| GPT-5 (OpenAI) | 94.3% |
| GPT-5.1 (OpenAI) | 94.0% |
| gpt-oss-120b (OpenAI) | 93.4% |
| GPT-5.1-Codex-Mini (OpenAI) | 91.7% |
| GPT-5 Mini (OpenAI) | 90.7% |
| o4 Mini High (OpenAI) | 90.7% |
MMLU-Pro
Percentage correct · higher is better
- Claude Opus 4.5Anthropic88.9%
- M2.1MiniMax87.5%
- GPT-5.2OpenAI87.4%
- GPT-5OpenAI87.1%
- GPT-5.1OpenAI87.0%
- Gemini 2.5 ProGoogle86.2%
- GPT-5.1-CodexOpenAI86.0%
- Claude Sonnet 4.5Anthropic86.0%
- Claude Opus 4Anthropic86.0%
- GLM 4.7Z.ai85.6%
Broad multi-task knowledge, harder distractors than MMLU.
View as table
| Model | Score |
|---|---|
| Claude Opus 4.5 (Anthropic) | 88.9% |
| M2.1 (MiniMax) | 87.5% |
| GPT-5.2 (OpenAI) | 87.4% |
| GPT-5 (OpenAI) | 87.1% |
| GPT-5.1 (OpenAI) | 87.0% |
| Gemini 2.5 Pro (Google) | 86.2% |
| GPT-5.1-Codex (OpenAI) | 86.0% |
| Claude Sonnet 4.5 (Anthropic) | 86.0% |
| Claude Opus 4 (Anthropic) | 86.0% |
| GLM 4.7 (Z.ai) | 85.6% |
IFBench
Percentage correct · higher is better
- MiniMax M3MiniMax82.9%
- Grok 4.3xAI81.3%
- Grok 4.20xAI81.2%
- Qwen3.7 MaxQwen80.5%
- MiMo-V2.5-ProXiaomi79.9%
- 78.8%
- Qwen3.7 PlusQwen78.0%
- GPT-5.2-CodexOpenAI77.6%
- Gemini 3.1 Flash LiteGoogle77.2%
- 77.2%
Precise instruction following under explicit constraints.
View as table
| Model | Score |
|---|---|
| MiniMax M3 (MiniMax) | 82.9% |
| Grok 4.3 (xAI) | 81.3% |
| Grok 4.20 (xAI) | 81.2% |
| Qwen3.7 Max (Qwen) | 80.5% |
| MiMo-V2.5-Pro (Xiaomi) | 79.9% |
| Qwen3.5 397B A17B (Qwen) | 78.8% |
| Qwen3.7 Plus (Qwen) | 78.0% |
| GPT-5.2-Codex (OpenAI) | 77.6% |
| Gemini 3.1 Flash Lite (Google) | 77.2% |
| Gemini 3.1 Flash Lite Preview (Google) | 77.2% |
Cross-section
The frontier, benchmark by benchmark
The top twelve models on the Intelligence Index, and how each one actually did on the tests behind it.
Frontier models across six evaluations
Percentage correct · darker means stronger
| Model | GPQA Diamond | Humanity's Last Exam | SciCode | τ²-bench | Terminal-Bench Hard | AA-LCR |
|---|---|---|---|---|---|---|
| Qwen3.8 MaxQwen | 93% | 43% | 53% | 51% | — | 74% |
| Claude Opus 5.5Anthropic | — | 61% | 67% | — | — | 85% |
| Claude Sonnet 5.5Anthropic | — | 55% | 61% | — | — | 83% |
| Claude Fable 5.1Anthropic | 94% | 59% | 63% | 47% | — | 85% |
| GPT-6 AstraOpenAI | 96% | 55% | 56% | 41% | — | 81% |
| Gemini 4 ArgonGoogle | — | 57% | 62% | — | — | 80% |
| Muse WonderMeta | — | 50% | 60% | — | — | 81% |
| GPT-6.1 SolOpenAI | — | 53% | 54% | — | — | 83% |
| Claude Opus 5Anthropic | 93% | 55% | 56% | 42% | — | 79% |
| Claude Fable 5Anthropic | 93% | 56% | 61% | 99% | 63% | 82% |
| Muse Spark 1.3Meta | 94% | 49% | 59% | 51% | — | 83% |
| GPT-6 SolOpenAI | — | 48% | 58% | — | — | 84% |
0%High
Read across a row to see a model's shape, down a column to see which test separates the field. Blank means not run.
View as table
| Model | GPQA Diamond | Humanity's Last Exam | SciCode | τ²-bench (Telecom) | Terminal-Bench Hard | AA-LCR (long context) |
|---|---|---|---|---|---|---|
| Qwen3.8 Max | 92.7% | 43.0% | 52.9% | 51.3% | — | 74.3% |
| Claude Opus 5.5 | — | 61.4% | 66.9% | — | — | 84.7% |
| Claude Sonnet 5.5 | — | 55.0% | 61.0% | — | — | 82.7% |
| Claude Fable 5.1 | 93.7% | 59.1% | 63.1% | 47.2% | — | 85.3% |
| GPT-6 Astra | 96.1% | 54.7% | 56.5% | 41.4% | — | 80.7% |
| Gemini 4 Argon | — | 57.1% | 61.8% | — | — | 79.7% |
| Muse Wonder | — | 50.1% | 60.3% | — | — | 80.7% |
| GPT-6.1 Sol | — | 52.9% | 54.2% | — | — | 83.0% |
| Claude Opus 5 | 93.2% | 54.9% | 56.4% | 42.1% | — | 79.3% |
| Claude Fable 5 | 92.6% | 55.5% | 61.0% | 98.5% | 62.9% | 82.3% |
| Muse Spark 1.3 | 93.5% | 48.7% | 58.8% | 50.5% | — | 83.0% |
| GPT-6 Sol | — | 47.9% | 57.6% | — | — | 83.7% |
Economics
Cost and responsiveness
The two boards where a low number wins.
Cheapest per task
Estimated USD · lower is better
- V4 Flash 0423DeepSeek$0.02
- Ling 3.1 FlashInclusionAI$0.02
- MiMo-V2.6-FlashXiaomi$0.03
- Claude Haiku 5.5Anthropic$0.04
- GPT-6 LunaOpenAI$0.04
- KAT-Coder-Pro V2KwaiPilot$0.04
- GLM 5.3 FlashZ.ai$0.05
- V4 Flash 0731DeepSeek$0.05
- Ring-2.6-1TInclusionAI$0.05
- V4.1 FlashDeepSeek$0.07
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning). Limited to models scoring 30+ on the Intelligence Index.
View as table
| Model | Cost / task | Intelligence |
|---|---|---|
| V4 Flash 0423 (DeepSeek) | $0.02 | 34.3 |
| Ling 3.1 Flash (InclusionAI) | $0.02 | 41.1 |
| MiMo-V2.6-Flash (Xiaomi) | $0.03 | 37.9 |
| Claude Haiku 5.5 (Anthropic) | $0.04 | 43.4 |
| GPT-6 Luna (OpenAI) | $0.04 | 38.1 |
| KAT-Coder-Pro V2 (KwaiPilot) | $0.04 | 33.9 |
| GLM 5.3 Flash (Z.ai) | $0.05 | 41.8 |
| V4 Flash 0731 (DeepSeek) | $0.05 | 34.3 |
| Ring-2.6-1T (InclusionAI) | $0.05 | 31.1 |
| V4.1 Flash (DeepSeek) | $0.07 | 39.5 |
Lowest latency
Seconds to first token · lower is better
- 64ms
- Gemma 4 31BGoogle89ms
- Phi 4Microsoft98ms
- Granite 4.1 8BIBM Granite118ms
- Llama 3 8B LunarisSao10K143ms
- 151ms
- 168ms
- gpt-oss-safeguard-20bOpenAI177ms
- Nemotron 3.5 LightningNVIDIA194ms
- Mistral Small 4Mistral AI194ms
Median time to first token.
View as table
| Model | Latency |
|---|---|
| Llama 3.1 8B Instruct (Meta) | 64ms |
| Gemma 4 31B (Google) | 89ms |
| Phi 4 (Microsoft) | 98ms |
| Granite 4.1 8B (IBM Granite) | 118ms |
| Llama 3 8B Lunaris (Sao10K) | 143ms |
| Llama 3.3 70B Instruct (Meta) | 151ms |
| Nemotron 3.5 Content Safety (NVIDIA) | 168ms |
| gpt-oss-safeguard-20b (OpenAI) | 177ms |
| Nemotron 3.5 Lightning (NVIDIA) | 194ms |
| Mistral Small 4 (Mistral AI) | 194ms |
404 models considered for every board on this page.