Higher-scoring or cheaper alternatives
138 of the 144 models carrying both an independent score and a standard-delivery price have a higher-scoring or cheaper alternative, with neither dimension worse. Each has a page naming the models and workloads, with recorded capabilities preserved or specific losses identified. The undominated remainder is on the value frontier.
Ordered by the largest measured saving. Prices are blended per million tokens on a balanced workload, as of 2026-10-16, except 10 prices marked under confirmation: the last we published, kept until a second day shows upstream’s new figure. A page here exists only while the finding does — when no candidate improves score or price without worsening the other under a listed workload, the page stops being built.
| Model | Provider | Arena Elo | $/M | Recorded capabilities preserved | Recorded capability losses | Best saving |
|---|---|---|---|---|---|---|
| Claude Opus 4.1 | Anthropic | 1418.5 | $30.00 | 35 | 36 | >99% |
| GPT-4 Turbo | OpenAI | 1271.6 | $15.00 | 85 | 44 | >99% |
| o1 | OpenAI | 1365.8 | $26.25 | 35 | 68 | >99% |
| Claude Opus 4.5 | Anthropic | 1450.9 | $10.00 | 20 | 11 | −99% |
| Claude Opus 4.8 | Anthropic | 1461.1 | $10.00 | 9 | 14 | −99% |
| Command R+ (08-2024) | Cohere | 1228.9 | $4.38 | 113 | 8 | −99% |
| GPT-4o (2024-05-13) | OpenAI | 1300.4 | $7.50 | 50 | 69 | −99% |
| GPT-4o (2024-08-06) | OpenAI | 1282.5 | $4.38 | 40 | 71 | −99% |
| GPT-6 Astra | OpenAI | 1442.1 | $20.00 | 5 | 38 | −99% |
| Mistral Large 2407 | Mistral | 1266.1 | $3.00 | 16 | 87 | −99% |
| Claude Sonnet 4.5 | Anthropic | 1438.5 | $6.00 | 15 | 20 | −98% |
| Claude Sonnet 4.6 | Anthropic | 1457.8 | $6.00 | 4 | 13 | −98% |
| GPT-5 | OpenAI | 1406.2 | $3.44 | 8 | 52 | −98% |
| GPT-5.1 | OpenAI | 1422.2 | $3.44 | 6 | 38 | −98% |
| GPT-5.2 | OpenAI | 1412.2 | $4.81 | 11 | 51 | −98% |
| GPT-5.4 | OpenAI | 1452.2 | $5.63 | 0 | 21 | −98% |
| GPT-5.5 | OpenAI | 1466.9 | $11.25 | 0 | 20 | −98% |
| GPT-5.6 Sol | OpenAI | 1457.2 | $8.00 | 0 | 22 | −98% |
| GPT-6 Sol | OpenAI | 1397.3 | $4.00 | 2 | 65 | −98% |
| Claude Sonnet 5 | Anthropic | 1442.4 | $4.00 | 5 | 21 | −97% |
| Gemma 2 27B | 1231.3 | $0.650 | 77 | 0 | −97% | |
| GPT-4.1 | OpenAI | 1382.8 | $3.50 | 14 | 60 | −97% |
| GPT-5.6 Terra | OpenAI | 1446.8 | $4.50 | 1 | 22 | −97% |
| GPT-6.1 Sol | OpenAI | 1447.5 | $4.00 | 0 | 21 | −97% |
| Grok 4.6 | xAI | 1428.2 | $3.00 | 4 | 36 | −97% |
| Grok 4.7 | xAI | 1400.6 | $3.00 | 5 | 57 | −97% |
| Llama 3.1 70B Instruct | Meta | 1260.9 | $0.720 | 70 | 8 | −97% |
| Mistral Medium 3.5 | Mistral | 1421.1 | $3.00 | 5 | 44 | −97% |
| o3 | OpenAI | 1409.9 | $3.50 | 11 | 49 | −97% |
| o3 Mini | OpenAI | 1319.4 | $1.93 | 12 | 72 | −97% |
| o3 Mini High | OpenAI | 1336.5 | $1.93 | 10 | 68 | −97% |
| o4 Mini | OpenAI | 1353.2 | $1.93 | 9 | 62 | −97% |
| Qwen2.5 Coder 32B Instruct | Qwen | 1230 | $0.745 | 64 | 16 | −97% |
| Claude Haiku 4.5 | Anthropic | 1396.5 | $2.00 | 10 | 44 | −96% |
| Claude Opus 4.7 | Anthropic | 1489.7 | $10.00 | 5 | 3 | −96% |
| Grok 4.5 | xAI | 1448 | $3.00 | 3 | 16 | −96% |
| Claude Sonnet 5.5 | Anthropic | 1470.6 | $4.00 | 3 | 8 | −95% |
| Gemini 2.5 Pro | 1457.7 | $3.44 | 7 | 8 | −95% | |
| GPT-5.4 Mini | OpenAI | 1411.6 | $1.69 | 1 | 43 | −95% |
| Mistral Large 4 | Mistral | 1429.7 | $2.07 | 5 | 29 | −95% |
| Qwen2.5 72B Instruct | Qwen | 1269 | $0.370 | 56 | 2 | −95% |
| GLM 5V Turbo | Z.ai | 1437.5 | $1.90 | 8 | 15 | −94% |
| Nova 2 Lite | Amazon | 1361.8 | $0.850 | 3 | 47 | −94% |
| Qwen3 235B A22B Thinking 2507 | Qwen | 1415 | $1.21 | 36 | 3 | −94% |
| R1 | DeepSeek | 1372.6 | $1.15 | 51 | 5 | −94% |
| GLM 4.5V | Z.ai | 1332.6 | $0.900 | 27 | 32 | −93% |
| Grok 4.3 | xAI | 1396.8 | $1.56 | 0 | 47 | −93% |
| MiniMax M1 | MiniMax | 1342.6 | $0.850 | 19 | 37 | −93% |
| Gemini 3.1 Pro Preview | 1480.3 | $4.50 | 4 | 1 | −92% | |
| Inkling | Thinking Machines | 1441.2 | $1.73 | 0 | 15 | −92% |
| R1 0528 | DeepSeek | 1427.7 | $0.920 | 25 | 2 | −92% |
| Step 5 Preview | StepFun | 1440 | $1.43 | 4 | 11 | −92% |
| DeepSeek V4 Pro 0423 | DeepSeek | 1445.4 | $1.21Price under confirmation since Oct 12, 2026 | 3 | 7 | −91% |
| Gemini 2.5 Flash | 1417 | $0.850 | 1 | 29 | −91% | |
| GLM 4.5 | Z.ai | 1430 | $1.00 | 19 | 3 | −91% |
| GPT-4.1 Mini | OpenAI | 1340.4 | $0.700 | 5 | 40 | −91% |
| Kimi K2.5 | Moonshot AI | 1445 | $1.20 | 2 | 9 | −90% |
| Llama 3.3 70B Instruct | Meta | 1274.2 | $0.280 | 21 | 9 | −90% |
| MiniMax M2 | MiniMax | 1340 | $0.525 | 16 | 32 | −90% |
| Qwen3.5-122B-A10B | Qwen | 1417.5 | $0.715 | 8 | 15 | −90% |
| Command R (08-2024) | Cohere | 1187.3 | $0.263 | 30 | 5 | −89% |
| DeepSeek V3 | DeepSeek | 1332.4 | $0.500Price under confirmation since Oct 16, 2026 | 37 | 8 | −89% |
| Gemini 3.5 Flash | 1477.6 | $3.38 | 6 | 1 | −89% | |
| GLM 5 | Z.ai | 1446.1 | $1.09 | 9 | 0 | −89% |
| GLM 5.1 | Z.ai | 1462.6 | $1.83 | 9 | 1 | −89% |
| GPT-4o-mini (2024-07-18) | OpenAI | 1286.3 | $0.263 | 2 | 25 | −89% |
| GPT-5 Mini | OpenAI | 1373.2 | $0.688 | 2 | 32 | −89% |
| Kimi K3 | Moonshot AI | 1475.6 | $3.05Price under confirmation since Oct 13, 2026 | 3 | 5 | −89% |
| Qwen3.5 397B A17B | Qwen | 1437.9 | $0.878 | 1 | 13 | −89% |
| GLM 4.7 | Z.ai | 1435.5 | $1.00Price under confirmation since Oct 16, 2026 | 13 | 3 | −88% |
| MiniMax M2.5 | MiniMax | 1359.2 | $0.521 | 18 | 14 | −88% |
| Gemini 3.5 Flash Lite | 1434.7 | $0.850 | 0 | 14 | −87% | |
| Gemini 3.7 Flash | 1487.1 | $3.00 | 2 | 1 | −87% | |
| Qwen3.6 Plus | Qwen | 1436.4 | $0.731 | 4 | 8 | −87% |
| Qwen3.8 27B | Qwen | 1440.6 | $0.956 | 0 | 11 | −87% |
| Gemini 3.1 Flash Lite Preview | 1415.8 | $0.563 | 0 | 20 | −86% | |
| Qwen3.5-27B | Qwen | 1409 | $0.536 | 6 | 16 | −86% |
| Claude Fable 5 | Anthropic | 1491 | $20.00 | 5 | 2 | −85% |
| Llama 3.2 3B Instruct | Meta | 1109.5 | $0.120 | 9 | 7 | −85% |
| Trinity Large Thinking | Arcee | 1340.1 | $0.388 | 11 | 15 | −85% |
| DeepSeek V3.1 | DeepSeek | 1419.7 | $0.453 | 14 | 2 | −84% |
| DeepSeek V3.1 Terminus | DeepSeek | 1417.4 | $0.453 | 6 | 12 | −84% |
| GLM 5.2 | Z.ai | 1470 | $1.12Price under confirmation since Oct 12, 2026 | 1 | 2 | −84% |
| GPT-4.1 Nano | OpenAI | 1284.7 | $0.175 | 0 | 16 | −84% |
| Inkling Small | Thinking Machines | 1412.2 | $0.638 | 0 | 25 | −84% |
| Kimi K2.6 | Moonshot AI | 1455.4 | $0.825 | 1 | 4 | −84% |
| Mercury 2 | Inception | 1355 | $0.375 | 17 | 7 | −84% |
| DeepSeek V3 0324 | DeepSeek | 1374.6 | $0.438 | 19 | 11 | −83% |
| GLM 4.6 | Z.ai | 1439.9 | $0.760 | 7 | 1 | −83% |
| GPT-5.4 Nano | OpenAI | 1372.1 | $0.463 | 2 | 25 | −83% |
| MiniMax M2.7 | MiniMax | 1404.5 | $0.525 | 9 | 12 | −83% |
| Solar Pro 4 | Upstage | 1387.4 | $0.525 | 8 | 18 | −83% |
| GPT-5.6 Luna | OpenAI | 1430.6 | $0.450 | 0 | 10 | −82% |
| Qwen3 Next 80B A3B Thinking | Qwen | 1368.2 | $0.413 | 4 | 27 | −82% |
| Qwen3 Next 80B A3B Instruct | Qwen | 1417 | $0.343 | 12 | 2 | −80% |
| DeepSeek V3.2 Exp | DeepSeek | 1422.1 | $0.305 | 5 | 8 | −79% |
| Qwen3.5-35B-A3B | Qwen | 1394.5 | $0.355 | 6 | 9 | −79% |
| GLM 4.6V | Z.ai | 1376.3 | $0.450 | 7 | 15 | −78% |
| Muse Spark 1.1 | Meta | 1478.1 | $2.00 | 2 | 2 | −78% |
| Muse Spark 1.2 | Meta | 1484.9 | $2.00 | 1 | 1 | −78% |
| Muse Spark 1.3 | Meta | 1489.8 | $2.00 | 0 | 1 | −78% |
| Qwen3 32B | Qwen | 1340 | $0.248 | 17 | 5 | −78% |
| Qwen3 VL 235B A22B Instruct | Qwen | 1420.2 | $0.370 | 7 | 6 | −77% |
| Qwen3.7 Plus | Qwen | 1454.6 | $0.560 | 4 | 1 | −77% |
| Llama 3.2 1B Instruct | Meta | 1054.6 | $0.071 | 3 | 5 | −76% |
| GLM 4.5 Air | Z.ai | 1383.7 | $0.310 | 10 | 5 | −75% |
| Gemini 3.6 Flash | 1479.5 | $1.50 | 0 | 1 | −74% | |
| MiniMax M3 | MiniMax | 1433.4 | $0.485 | 0 | 8 | −74% |
| Phi 4 | Microsoft | 1216.6 | $0.088 | 12 | 0 | −74% |
| Qwen3 30B A3B | Qwen | 1316.8 | $0.215 | 17 | 4 | −74% |
| DeepSeek V3.2 | DeepSeek | 1424.5 | $0.290 | 3 | 6 | −71% |
| GLM 5.3 | Z.ai | 1471.4 | $1.00Price under confirmation since Oct 12, 2026 | 0 | 1 | −69% |
| Mistral Small 3 | Mistral | 1233.5 | $0.058 | 3 | 0 | −63% |
| Qwen3 235B A22B Instruct 2507 | Qwen | 1419.1 | $0.205 | 8 | 2 | −62% |
| GLM 4.7 Flash | Z.ai | 1350.6 | $0.145 | 6 | 5 | −61% |
| Claude Fable 5.1 | Anthropic | 1509.9 | $20.00 | 1 | 1 | −60% |
| GPT-5 Nano | OpenAI | 1320 | $0.138 | 0 | 10 | −60% |
| MiMo-V2.5-Pro | Xiaomi | 1465.1 | $0.544Price under confirmation since Oct 16, 2026 | 1 | 1 | −60% |
| GPT-6 Luna | OpenAI | 1391.5 | $0.200 | 0 | 9 | −58% |
| Gemma 3 27B | 1357.7 | $0.100 | 4 | 3 | −57% | |
| Gemma 4 31B | 1442.9 | $0.205 | 2 | 1 | −57% | |
| Step 3.5 Flash | StepFun | 1402.8 | $0.150 | 5 | 0 | −53% |
| Qwen3 30B A3B Instruct 2507 | Qwen | 1383.7 | $0.143 | 3 | 4 | −50% |
| Hy3 | Tencent | 1437.4 | $0.231 | 3 | 1 | −46% |
| Granite 4.2 8B | IBM | 1319.6 | $0.108 | 2 | 3 | −44% |
| MiMo-V2.5 | Xiaomi | 1427.8 | $0.175 | 1 | 3 | −38% |
| Qwen3.5-Flash | Qwen | 1397.2 | $0.114 | 2 | 3 | −36% |
| Gemma 3 12B | 1334.2 | $0.075Price under confirmation since Oct 16, 2026 | 0 | 2 | −35% | |
| MiMo-V2.6-Flash | Xiaomi | 1455.2 | $0.168 | 0 | 1 | −34% |
| gpt-oss-20b | OpenAI | 1287.4 | $0.036 | 0 | 1 | −27% |
| Claude Opus 4.6 | Anthropic | 1501.8 | $10.00 | 3 | 1 | −22% |
| Claude Opus 5 | Anthropic | 1502.5 | $10.00 | 2 | 1 | −22% |
| Gemma 4 26B A4B | 1433.9 | $0.128 | 0 | 2 | −14% | |
| DeepSeek V4 Flash 0423 | DeepSeek | 1432.2 | $0.113Price under confirmation since Oct 12, 2026 | 1 | 1 | −10% |
| Llama 3.1 8B Instruct | Meta | 1186.5 | $0.025 | 0 | 1 | −9% |
| DeepSeek V4.1 Flash | DeepSeek | 1462.5 | $0.182Price under confirmation since Oct 12, 2026 | 0 | 1 | −3% |
| Claude Opus 5.5 | Anthropic | 1515.5 | $8.00 | 0 | 1 | −0% |
| Muse Wonder | Meta | 1503.9 | $8.00 | 0 | 2 | −0% |
Both columns count candidates with a higher score or a lower price, with neither dimension worse. Recorded capabilities preserved also requires matching or beating the recorded context, maximum output, input modes, tool use and extended reasoning. Recorded capability losses counts candidates with a reduction in at least one of those; each loss is named on the model's page. Savings are rounded to whole percentages, so a saving shown as >99% is not a free model. Scores are LMArena Elo, used under CC BY 4.0 from the official dataset. Models with no independent score are absent from this comparison in both directions — unrated is not a zero.
Questions this page answers
What does dominated mean on this index?
At least one other standard-delivery catalogue model has a higher score or a lower price, with neither dimension worse, under a listed workload. The columns distinguish preserved recorded capabilities from named losses. Models with no independent score are absent in both directions.
What distinguishes the two kinds of alternative?
Both improve score or price without worsening the other. Recorded capabilities preserved means matching or beating the recorded context, maximum output, input modes, tools and extended reasoning. Recorded capability losses means at least one of those is reduced; each loss is named on the model page.
Why can a page disappear?
Each /alternatives/<slug>/ page is built only while a candidate improves score or price without worsening the other under a listed workload. When that comparison no longer holds, the page stops being generated.