Glsrm Benchmarks · July 26, 2026
Independent vibe check of AI
Understand the AI landscape to choose the best model and provider for your use case — intelligence, speed, and cost, measured independently.
Frontier models
43
Labs tracked
18
Evals in the index
9
Snapshot
July 26, 2026
Highlights
Higher is better
Intelligence
Intelligence Index · best model per lab
- 1
Claude Opus 5 (max)61 - 2
GPT-5.6 Sol (max)59 - 3
Kimi K357 - 4
Grok 4.5 (high)54 - 5
GLM-5.2 (max)51 - 6
Muse Spark 1.1 (xhigh)51 - 7
Gemini 3.5 Flash50 - 8
Qwen3.7 Max46 - 9
MiniMax-M344
Higher is better
Speed
Median output tokens per second · best per lab
- 1Qwen3.7 Max197
- 2Command A+197
- 3GLM-5.2 (max)191
- 4Gemini 3.5 Flash185
- 5
Nemotron 3 Ultra182 - 6Muse Spark 1.1 (xhigh)117
- 7
Nova 2.0 Pro Preview (medium)115 - 8
Mistral Medium 3.585 - 9Inkling82
Lower is better
Price
USD per 1M tokens, 3:1 blended · cheapest per lab
- 1MiniMax-M3$0.53
- 2
DeepSeek V4 Pro (max)$0.54 - 3
MiMo-V2.5-Pro$0.54 - 4Nemotron 3 Ultra$1.18
- 5Muse Spark 1.1 (xhigh)$2.00
- 6GLM-5.2 (max)$2.15
- 7Inkling$2.57
- 8Grok 4.5 (high)$3.00
- 9Mistral Medium 3.5$3.00
Model comparison summary
Every model we track, ranked by Intelligence Index.
| # | Model | Creator | Released | Context | Intelligence | Coding | Agentic | Speed (t/s) | Blended $/1M | Latency |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5 (max) | Anthropic | Jul 2026 | 1M | 61 | 78 | 55 | 53 | $10.00 | 68s |
| 2 | Claude Fable 5 (with fallback) | Anthropic | Jun 2026 | 1M | 60 | 77 | 53 | 71 | $20.00 | 112s |
| 3 | GPT-5.6 Sol (max) | OpenAI | Jul 2026 | 1M | 59 | 77 | 54 | 66 | $11.25 | 145s |
| 4 | Kimi K3 | Kimi | Jul 2026 | 1.0M | 57 | 76 | 50 | 32 | $6.00 | 252s |
| 5 | Claude Opus 4.8 (max) | Anthropic | May 2026 | 1M | 56 | 74 | 47 | 56 | $10.00 | 30s |
| 6 | GPT-5.6 Terra (max) | OpenAI | Jul 2026 | 1M | 55 | 77 | 47 | 136 | $5.63 | 178s |
| 7 | GPT-5.5 (xhigh) | OpenAI | Apr 2026 | 922k | 55 | 75 | 45 | 79 | $11.25 | 89s |
| 8 | Grok 4.5 (high) | xAI | Jul 2026 | 500k | 54 | 72 | 46 | 61 | $3.00 | 10s |
| 9 | Claude Opus 4.7 (max) | Anthropic | Apr 2026 | 1M | 54 | 74 | 44 | 50 | $10.00 | 26s |
| 10 | Claude Sonnet 5 (max) | Anthropic | Jun 2026 | 1M | 53 | 72 | 47 | 76 | $4.00 | 192s |
| 11 | GPT-5.6 Luna (max) | OpenAI | Jul 2026 | 1M | 51 | 71 | 46 | 188 | $2.25 | 139s |
| 12 | GLM-5.2 (max)Open | Z AI | Jun 2026 | 1M | 51 | 69 | 43 | 191 | $2.15 | 12s |
| 13 | Muse Spark 1.1 (xhigh) | Meta | Jul 2026 | 1.0M | 51 | 71 | 38 | 117 | $2.00 | 19s |
| 14 | Gemini 3.5 Flash | May 2026 | 1M | 50 | 70 | 37 | 185 | $3.38 | 22s | |
| 15 | Gemini 3.6 Flash | Jul 2026 | 1M | 50 | 69 | 39 | 231 | $3.00 | 19s | |
| 16 | Claude Sonnet 4.6 (max) | Anthropic | Feb 2026 | 1M | 47 | 63 | 41 | 46 | $6.00 | 150s |
| 17 | Gemini 3.1 Pro Preview | Feb 2026 | 1M | 47 | 69 | 21 | 124 | $4.50 | 35s | |
| 18 | Qwen3.7 Max | Alibaba | May 2026 | 1M | 46 | 66 | 31 | 197 | $3.75 | 15s |
| 19 | MiniMax-M3Open | MiniMax | Jun 2026 | 1M | 44 | 59 | 35 | 76 | $0.53 | 28s |
| 20 | GPT-5.3 Codex (xhigh) | OpenAI | Feb 2026 | 400k | 44 | — | — | 134 | $4.81 | 66s |
| 21 | DeepSeek V4 Pro (max)Open | DeepSeek | Apr 2026 | 1M | 44 | 59 | 36 | 67 | $0.54 | 67s |
| 22 | Kimi K2.6Open | Kimi | Apr 2026 | 256k | 44 | 62 | 30 | 35 | $1.71 | 131s |
| 23 | Muse Spark | Meta | Apr 2026 | 262k | 43 | 59 | 29 | — | — | — |
| 24 | MiMo-V2.5-ProOpen | Xiaomi | Apr 2026 | 1M | 42 | 60 | 29 | 69 | $0.54 | 32s |
| 25 | Thinking Machines | Jul 2026 | 1M | 41 | 52 | 32 | 82 | $2.57 | 26s | |
| 26 | DeepSeek V4 Flash (max)Open | DeepSeek | Apr 2026 | 1M | 40 | 56 | 31 | 121 | $0.18 | 47s |
| 27 | GLM-5.1Open | Z AI | Apr 2026 | 200k | 40 | 56 | 30 | 65 | $2.14 | 60s |
| 28 | GPT-5.4 mini (xhigh) | OpenAI | Mar 2026 | 400k | 40 | 56 | 30 | 175 | $1.69 | 8.8s |
| 29 | Qwen3.7 Plus | Alibaba | Jun 2026 | 1M | 39 | 56 | 21 | 54 | $0.70 | 40s |
| 30 | MiniMax-M2.7Open | MiniMax | Mar 2026 | 205k | 38 | 53 | 26 | 58 | $0.53 | 44s |
| 31 | Nemotron 3 UltraOpen | NVIDIA | Jun 2026 | 262k | 38 | 49 | 27 | 182 | $1.18 | 14s |
| 32 | Grok 4.3 (high) | xAI | Apr 2026 | 1M | 38 | 42 | 24 | 117 | $1.56 | 28s |
| 33 | Gemini 3.5 Flash-Lite | Jul 2026 | 1M | 37 | 49 | 27 | 399 | $0.85 | 9.4s | |
| 34 | Qwen3.5 397B A17BOpen | Alibaba | Feb 2026 | 262k | 34 | 48 | 20 | 69 | $1.35 | 49s |
| 35 | Mistral Medium 3.5Open | Mistral | Apr 2026 | 256k | 30 | 47 | 19 | 85 | $3.00 | 26s |
| 36 | Claude 4.5 Haiku | Anthropic | Oct 2025 | 200k | 30 | 44 | 16 | 92 | $2.00 | 12s |
| 37 | Gemma 4 31BOpen | Apr 2026 | 256k | 29 | 43 | 14 | 35 | — | 50s | |
| 38 | gpt-oss-120b (high)Open | OpenAI | Aug 2025 | 131k | 24 | 30 | 13 | 273 | $0.26 | 8.2s |
| 39 | Cohere | May 2026 | 192k | 23 | 28 | 9 | 197 | — | 11s | |
| 40 | Nova 2.0 Pro Preview (medium) | Amazon | Nov 2025 | 256k | 22 | 34 | 7 | 115 | $3.44 | 33s |
| 41 |  K2 Think V2Open | MBZUAI IFM | Dec 2025 | 262k | 17 | 21 | 2 | — | — | — |
| 42 |  Solar Pro 3 | Upstage | Apr 2026 | 128k | 14 | 16 | 3 | — | — | — |
| — | GPT-5.5 Pro (xhigh) | OpenAI | Apr 2026 | 922k | — | — | — | — | — | — |
Intelligence Index
Composite of 10 evaluations spanning reasoning, knowledge, math, coding, and agentic tool use. Higher is better.
Incorporates GPQA Diamond, Humanity's Last Exam, AIME 2025, LiveCodeBench, SciCode, IFBench, Terminal-Bench Hard, τ²-Bench, and more.
Intelligence vs. Price
Intelligence Index against blended USD per 1M tokens (3:1 input:output, log scale).
Up and to the left wins: more intelligence per dollar. Models without public API pricing are excluded.
Intelligence vs. Output Speed
Each dot is a model. Higher = smarter · farther right = faster. Purple guides mark market medians; named labels highlight the efficiency frontier.
Hover any dot for exact scores. The shaded corner is the sweet spot: above-median intelligence and above-median speed. Speed is the median tokens/s across providers serving each model.
Frontier Intelligence Over Time
Intelligence Index by release date. The dashed line tracks the running frontier.
Claude Opus 5 set the current frontier on July 24, 2026 — two days before this snapshot.
Coding Index
Composite of coding evaluations (LiveCodeBench, SciCode, Terminal-Bench Hard). Higher is better.
Agentic Index
Tool calling and long-horizon agent tasks (τ²-Bench, Terminal-Bench). Higher is better.
Intelligence Breakdown
Individual evaluation scores (0–100) behind the Intelligence Index. Darker is better, normalized per column.
| Model | GPQA Diamond | Humanity's Last Exam | SciCode | IFBench | Terminal-Bench Hard | τ²-Bench Telecom | AA-LCR (Long Context) | CritPt | MMMU-Pro |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 (max) | 93.2 | 52.6 | 55.7 | — | — | — | 70.0 | 29.1 | 84.7 |
| Claude Fable 5 (with fallback) | 92.6 | 53.3 | 60.2 | 63.5 | 62.9 | 98.5 | 70.0 | 28.6 | — |
| GPT-5.6 Sol (max) | 94.1 | 47.2 | 56.1 | 72.7 | 65.9 | 85.1 | 73.7 | 32.3 | 83.4 |
| Kimi K3 | 93.5 | 44.3 | 58.7 | — | — | — | 74.7 | 23.4 | 80.5 |
| Claude Opus 4.8 (max) | 92.0 | 45.7 | 53.5 | 62.2 | 58.3 | 94.4 | 67.7 | 20.9 | — |
| GPT-5.6 Terra (max) | 92.5 | 41.8 | 53.9 | 71.2 | 57.6 | 86.3 | 74.0 | 30.0 | 80.7 |
| GPT-5.5 (xhigh) | 93.5 | 44.3 | 56.1 | 75.9 | 60.6 | 93.9 | 74.3 | 27.1 | 79.9 |
| Grok 4.5 (high) | 93.1 | 40.3 | 54.1 | — | — | — | 67.7 | 15.4 | 80.4 |
| Claude Opus 4.7 (max) | 91.4 | 39.6 | 54.5 | 58.6 | 51.5 | 88.6 | 70.3 | 12.0 | 78.8 |
| Claude Sonnet 5 (max) | 91.1 | 39.6 | 53.6 | — | — | — | 70.7 | 16.9 | 77.3 |
| GPT-5.6 Luna (max) | 91.1 | 37.2 | 52.5 | — | — | — | 74.0 | 20.6 | 78.6 |
| GLM-5.2 (max) | 89.5 | 40.1 | 50.5 | 73.3 | 50.8 | 99.1 | 71.3 | 20.9 | — |
| Muse Spark 1.1 (xhigh) | 89.8 | 45.1 | 58.2 | — | — | — | 63.3 | 15.1 | — |
| Gemini 3.5 Flash | 92.2 | 41.0 | 53.1 | 76.3 | 40.9 | 95.3 | 69.3 | 13.1 | 84.3 |
| Gemini 3.6 Flash | 92.8 | 38.3 | 52.7 | — | — | — | 69.7 | 10.6 | 83.2 |
| Claude Sonnet 4.6 (max) | 87.5 | 30.0 | 46.8 | 56.6 | 53.0 | 75.7 | 70.7 | 3.1 | 73.3 |
| Gemini 3.1 Pro Preview | 94.1 | 44.7 | 58.9 | 77.1 | 53.8 | 95.6 | 72.7 | 17.7 | 82.4 |
| Qwen3.7 Max | 92.3 | 38.1 | 48.8 | 80.5 | 50.8 | 94.7 | 69.0 | 13.4 | — |
| MiniMax-M3 | 92.9 | 37.1 | 45.4 | 82.9 | 42.4 | 88.9 | 74.0 | 3.7 | 78.6 |
| GPT-5.3 Codex (xhigh) | 91.5 | 39.9 | 53.2 | 75.4 | 53.0 | 86.0 | 74.0 | 16.9 | 78.5 |
| DeepSeek V4 Pro (max) | 88.8 | 35.9 | 50.0 | 76.5 | 46.2 | 96.2 | 66.3 | 12.9 | — |
| Kimi K2.6 | 91.1 | 35.9 | 53.5 | 76.0 | 43.9 | 95.9 | 69.7 | 8.0 | 79.4 |
| Muse Spark | 88.4 | 39.9 | 51.5 | 75.9 | 45.5 | 91.5 | 69.7 | 11.3 | 80.5 |
| MiMo-V2.5-Pro | 86.6 | 33.8 | 50.2 | 79.9 | 43.2 | 94.2 | 73.3 | 4.0 | — |
| 87.2 | 29.7 | 46.1 | — | — | — | 63.3 | 5.4 | 73.5 | |
| DeepSeek V4 Flash (max) | 89.4 | 32.1 | 44.9 | 79.2 | 35.6 | 95.0 | 63.0 | 7.1 | — |
| GLM-5.1 | 86.8 | 28.0 | 43.8 | 76.3 | 43.2 | 97.7 | 62.3 | 4.6 | — |
| GPT-5.4 mini (xhigh) | 87.5 | 26.6 | 49.9 | 73.3 | 52.3 | 83.3 | 69.3 | 10.0 | 73.3 |
| Qwen3.7 Plus | 90.0 | 33.4 | 45.5 | 78.0 | 47.0 | 93.0 | 65.0 | 9.1 | 80.5 |
| MiniMax-M2.7 | 87.4 | 28.1 | 47.0 | 75.7 | 39.4 | 84.8 | 68.7 | 0.6 | — |
| Nemotron 3 Ultra | 86.7 | 26.6 | 39.9 | 81.4 | 36.4 | 83.3 | 67.0 | 3.1 | — |
| Grok 4.3 (high) | 90.1 | 35.0 | 47.3 | 81.3 | 37.9 | 97.7 | 64.3 | 8.0 | 78.1 |
| Gemini 3.5 Flash-Lite | 83.8 | 17.5 | 40.9 | — | — | — | 62.0 | 0.0 | 79.0 |
| Qwen3.5 397B A17B | 89.3 | 27.3 | 42.0 | 78.8 | 40.9 | 95.6 | 65.7 | 1.7 | 77.3 |
| Mistral Medium 3.5 | 74.8 | 12.8 | 39.6 | 68.8 | 33.3 | 94.2 | 61.0 | 0.0 | 64.9 |
| Claude 4.5 Haiku | 67.2 | 9.7 | 43.3 | 54.3 | 27.3 | 54.7 | 70.3 | 0.0 | 58.6 |
| Gemma 4 31B | 85.7 | 22.7 | 43.4 | 75.6 | 36.4 | 59.9 | 62.0 | 1.4 | 73.4 |
| gpt-oss-120b (high) | 78.2 | 18.5 | 38.9 | 69.0 | 23.5 | 65.8 | 50.7 | 1.1 | — |
| 76.1 | 11.4 | 37.8 | 73.9 | 25.0 | 80.7 | 46.0 | 0.3 | 63.2 | |
| Nova 2.0 Pro Preview (medium) | 78.5 | 8.9 | 42.7 | 79.0 | 24.2 | 92.7 | 54.3 | 0.0 | 64.5 |
| K2 Think V2 | 71.3 | 9.5 | 33.0 | 62.8 | 6.8 | 25.4 | 52.7 | 0.0 | — |
| Solar Pro 3 | 72.4 | 10.1 | 24.7 | 71.2 | 7.6 | 86.3 | 27.0 | 0.0 | — |
| GPT-5.5 Pro (xhigh) | — | — | — | — | — | — | — | 30.6 | — |
AIME 2025 and LiveCodeBench are retired for newer models and excluded here; MMMU-Pro applies to multimodal-evaluated models only.
Omniscience Index
Knowledge reliability from -100 to 100: correct answers score positive, hallucinated ones negative.
A negative score means the model hallucinates more than it knows. Declining to answer scores zero — most models would rather guess.
GDPval Elo — Real-World Work
Elo from blind pairwise comparisons on real economically valuable work tasks, with web and shell access.
Higher is better. Judged across occupations from software engineering to financial analysis.
ITBench — SRE Incident Analysis
Average precision at full recall diagnosing live Kubernetes incidents. Higher is better.
Models investigate real cluster telemetry to find root causes. Even the frontier tops out below 0.5 — ops work is far from solved.
Output Tokens Used to Run the Intelligence Suite
Total tokens generated answering the full evaluation suite, split into answer and reasoning tokens.
Reasoning-heavy models can burn 20–40× more tokens thinking than answering — which is exactly why blended price alone undersells true cost.
Cost to Run the Intelligence Suite
USD to complete every evaluation in the Intelligence Index, including reasoning tokens. Lower is better.
The spread is real: the same suite costs $19 on gpt-oss-20B and over $4,600 on the priciest frontier models.
Output Speed
Median output tokens per second across providers serving each model. Higher is better.
Latency — Time to First Answer Token
Seconds from request to first answer token, including reasoning time. Lower is better.
Max-effort reasoning modes pay for their scores in wait time: the smartest configurations routinely think for one to two minutes.
Pricing — Input and Output
USD per 1M tokens by direction. Lower is better.
Output tokens typically cost 2–4× input. Reasoning tokens bill as output, so thinking models multiply effective price.
Context Window
Maximum input tokens per request.
Openness Index
Weights availability plus transparency of methodology and training data, 0–100.
Only models with published openness scores shown. K2 Think V2 and Nemotron 3 Ultra lead; most frontier labs publish nothing.
Latest Insights
Reporting from the eval desk
How AI and Technology Are Reshaping Prop Firm Evaluations in 2026
By TechBullion · 2 hrs ago
Biggest challenge is convincing companies to invest in cybersecurity: SLT | Daily FT
By FT Sri Lanka · 2 hrs ago
Accountants embracing AI will outperform | Daily FT
By FT Sri Lanka · 2 hrs ago
Nvidia CEO Jensen Huang's first X post backs open AI models, gets support from Sundar Pichai - CNBC TV18
By cnbctv18.com · 2 hrs ago
Methodology: indices are composites of public evaluations run independently with standardized prompts; speed and latency are medians measured across API providers over the trailing 72 hours. Benchmark data: public model-evaluation snapshot, July 26, 2026. Prices are list API prices and change frequently. Company logos identify the respective model creators.